JP2019201332A - Image encoding device, image decoding device, and image encoding system - Google Patents

Abstract

To realize an encoding device for generating an encoded stream capable of identifying a neural network to be used by a decoding device itself.SOLUTION: The image encoding device includes an encoding unit (104) for generating encoded data by encoding a filtered image using a neural network. The encoding unit includes identification information for identifying the neural network from other neural networks in the encoded data.SELECTED DRAWING: Figure 6

Description

  Embodiments described herein relate generally to an image encoding device, an image decoding device, and an image encoding system.

  In order to efficiently transmit or record a moving image, a moving image encoding device that generates encoded data by encoding the moving image, and a moving image that generates a decoded image by decoding the encoded data An image decoding device is used.

  Specific examples of the moving image encoding method include a method proposed in H.264 / AVC and HEVC (High-Efficiency Video Coding).

  In such a moving image coding system, an image (picture) constituting a moving image is a slice obtained by dividing the image, a coding tree unit (CTU: Coding Tree Unit) obtained by dividing the slice. ), A coding unit obtained by dividing the coding tree unit (sometimes referred to as a coding unit (CU)), and a prediction unit that is a block obtained by dividing the coding unit (PU) and a hierarchical structure composed of conversion units (TU), and encoded / decoded for each CU.

  In such a moving image coding method, a predicted image is usually generated based on a local decoded image obtained by encoding / decoding an input image, and the predicted image is generated from the input image (original image). A prediction residual obtained by subtraction (sometimes referred to as “difference image” or “residual image”) is encoded. Examples of the method for generating a predicted image include inter-screen prediction (inter prediction) and intra-screen prediction (intra prediction).

  Further, Non-Patent Document 1 can be cited as a technique for encoding and decoding moving images in recent years.

"Algorithm Description of Joint Exploration Test Model 5", JVET-E1001, Joint Video Exploration Team (JVET) of ITU-T SG 16 WP 3 and ISO / IEC JTC 1 / SC 29 / WG 11, 12-20 January 2017

  When transmitting and receiving images with deep learning between the encoding device and the decoding device, it is necessary to use a pair of neural networks between the devices. However, when the neural network is updated, there is a problem that the decoding device cannot identify which neural network should be applied to the encoded stream (encoded data) acquired from the encoding device. In addition, correct data (teacher data) is required for learning, and since an original image is usually used for this, learning processing is possible only on the encoding device side, and the decoding device has its own neural network. It cannot be learned and reproduced using only information existing on the decoding device side.

  An aspect of the present invention has been made in view of the above problems, and an object thereof is to realize an encoding device that generates an encoded stream that can identify a neural network to be used by the decoding device itself.

  In order to solve the above-described problem, in the image encoding device that generates encoded data according to an aspect of the present invention, encoding is performed from n in encoding a filtered image using a neural network. An encoding unit that generates data is included, and the encoding unit includes identification information for identifying the neural network from other neural networks in the encoded data.

  According to one aspect of the present invention, it is possible to realize an encoding device that generates an encoded stream that can identify a neural network to be used by the decoding device itself.

It is a figure which shows the hierarchical structure of the data of the encoding stream which concerns on this embodiment. It is a figure which shows the pattern of PU division | segmentation mode. (A) to (h) show the partition shapes when the PU partitioning modes are 2Nx2N, 2NxN, 2NxnU, 2NxnD, Nx2N, nLx2N, nRx2N, and NxN, respectively. It is a block diagram which shows the structure of the image coding apparatus which concerns on this embodiment. It is the schematic which shows the structure of the image decoding apparatus which concerns on this embodiment. It is the schematic which shows the structure of the inter estimated image generation part of the image coding apparatus which concerns on this embodiment. It is the schematic which shows the structure of the image coding apparatus which concerns on this embodiment. It is the schematic which shows the structure of the image decoding apparatus which concerns on this embodiment. It is the schematic which shows an example of the neural network which concerns on this embodiment. It is a figure which shows the deep learning network synchronous system which concerns on this embodiment. It is a figure which shows the deep learning network synchronous system which concerns on this embodiment. It is a figure which shows the deep learning network synchronous system which concerns on this embodiment. It is a figure which shows the data structure of the deep learning identification information which concerns on this embodiment. It is the figure shown about the structure of the transmitter which mounts the image coding apparatus which concerns on this embodiment, and the receiver which mounts an image decoding apparatus. (A) shows a transmission device equipped with an image encoding device, and (b) shows a reception device equipped with an image decoding device. It is the figure shown about the structure of the recording device carrying the image coding apparatus which concerns on this embodiment, and the reproducing | regenerating apparatus carrying an image decoding apparatus. (A) shows a recording device equipped with an image encoding device, and (b) shows a playback device equipped with an image decoding device. It is the schematic which shows the structure of the image transmission system which concerns on this embodiment.

(First embodiment)
Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  FIG. 15 is a schematic diagram illustrating a configuration of the image transmission system 1 according to the present embodiment.

  The image transmission system 1 is a system that transmits a code obtained by encoding an image to be encoded, decodes the transmitted code, and displays an image. The image transmission system 1 includes an image encoding device (moving image encoding device) 11, a network 21, an image decoding device (moving image decoding device) 31, and an image display device 41.

  An image T indicating a single layer image or a plurality of layers of images is input to the image encoding device 11. A layer is a concept used to distinguish a plurality of pictures when there are one or more pictures constituting a certain time. For example, when the same picture is encoded with a plurality of layers having different image quality and resolution, scalable encoding is performed, and when a picture of a different viewpoint is encoded with a plurality of layers, view scalable encoding is performed. When prediction is performed between pictures of a plurality of layers (inter-layer prediction, inter-view prediction), encoding efficiency is greatly improved. Further, even when prediction is not performed (simultaneous casting), encoded data can be collected.

  The network 21 transmits the encoded stream Te generated by the image encoding device 11 to the image decoding device 31. The network 21 is the Internet, a wide area network (WAN), a small network (LAN), or a combination thereof. The network 21 is not necessarily limited to a bidirectional communication network, and may be a unidirectional communication network that transmits broadcast waves such as terrestrial digital broadcasting and satellite broadcasting. The network 21 may be replaced with a storage medium that records an encoded stream Te such as a DVD (Digital Versatile Disc) or a BD (Blue-ray Disc).

  The image decoding device 31 decodes each encoded stream Te transmitted by the network 21, and generates one or a plurality of decoded images Td decoded.

  The image display device 41 displays all or part of one or a plurality of decoded images Td generated by the image decoding device 31. The image display device 41 includes, for example, a display device such as a liquid crystal display or an organic EL (Electro-luminescence) display. In addition, in the spatial scalable coding and SNR scalable coding, when the image decoding device 31 and the image display device 41 have a high processing capability, an enhancement layer image with a high image quality is displayed and only a lower processing capability is provided. Displays a base layer image that does not require higher processing capability and display capability as an extension layer.

<Operator>
The operators used in this specification are described below.

  >> is right bit shift, << is left bit shift, & is bitwise AND, | is bitwise OR, and | = is OR assignment operator.

  x? y: z is a ternary operator that takes y when x is true (other than 0) and takes z when x is false (0).

  Clip3 (a, b, c) is a function that clips c to a value greater than or equal to a and less than or equal to b, returns a if c <a, returns b if c> b, otherwise Is a function that returns c (where a <= b).

<Structure of encoded stream Te>
Prior to detailed description of the image encoding device 11 and the image decoding device 31 according to the present embodiment, a data structure of an encoded stream Te generated by the image encoding device 11 and decoded by the image decoding device 31 will be described. .

  FIG. 1 is a diagram illustrating a hierarchical structure of data in the encoded stream Te. The encoded stream Te illustratively includes a sequence and a plurality of pictures constituting the sequence. (A) to (f) of FIG. 1 respectively show an encoded video sequence defining a sequence SEQ, an encoded picture defining a picture PICT, an encoded slice defining a slice S, and an encoded slice defining a slice data It is a figure which shows the coding unit (Coding Unit; CU) contained in the coding tree unit contained in data and coding slice data, and a coding tree unit.

(Encoded video sequence)
In the encoded video sequence, a set of data referred to by the image decoding device 31 for decoding the sequence SEQ to be processed is defined. As shown in FIG. 1A, the sequence SEQ includes a video parameter set (Video Parameter Set), a sequence parameter set SPS (Sequence Parameter Set), a picture parameter set PPS (Picture Parameter Set), a picture PICT, and an addition. Includes SEI (Supplemental Enhancement Information). Here, the value indicated after # indicates the layer ID. Although FIG. 1 shows an example in which encoded data of # 0 and # 1, that is, layer 0 and layer 1, exists, the type of layer and the number of layers are not dependent on this.

  The video parameter set VPS is a set of encoding parameters common to a plurality of moving images, a plurality of layers included in the moving image, and encoding parameters related to individual layers in a moving image composed of a plurality of layers. A set is defined.

  In the sequence parameter set SPS, a set of encoding parameters referred to by the image decoding device 31 in order to decode the target sequence is defined. For example, the width and height of the picture are defined. A plurality of SPSs may exist. In that case, one of a plurality of SPSs is selected from the PPS.

  In the picture parameter set PPS, a set of encoding parameters referred to by the image decoding device 31 in order to decode each picture in the target sequence is defined. For example, a quantization width reference value (pic_init_qp_minus26) used for picture decoding and a flag (weighted_pred_flag) indicating application of weighted prediction are included. There may be a plurality of PPSs. In that case, one of a plurality of PPSs is selected from each picture in the target sequence.

(Encoded picture)
In the coded picture, a set of data referred to by the image decoding device 31 in order to decode the picture PICT to be processed is defined. As shown in FIG. 1B, the picture PICT includes slices S0 to S _NS-1 (NS is the total number of slices included in the picture PICT).

Hereinafter, when it is not necessary to distinguish each of the slices S0 to SNS _-1 , the subscripts may be omitted. The same applies to data included in an encoded stream Te described below and to which other subscripts are attached.

(Encoded slice)
In the coded slice, a set of data referred to by the image decoding device 31 for decoding the slice S to be processed is defined. As shown in FIG. 1C, the slice S includes a slice header SH and slice data SDATA.

  The slice header SH includes an encoding parameter group that is referred to by the image decoding device 31 in order to determine a decoding method of the target slice. Slice type designation information (slice_type) for designating a slice type is an example of an encoding parameter included in the slice header SH.

  As slice types that can be specified by the slice type specification information, (1) I slice using only intra prediction at the time of encoding, (2) P slice using unidirectional prediction or intra prediction at the time of encoding, (3) B-slice using unidirectional prediction, bidirectional prediction, or intra prediction at the time of encoding may be used.

  Note that the slice header SH may include a reference (pic_parameter_set_id) to the picture parameter set PPS included in the encoded video sequence.

(Encoded slice data)
In the encoded slice data, a set of data referred to by the image decoding device 31 for decoding the slice data SDATA to be processed is defined. The slice data SDATA includes a coding tree unit (CTU) as shown in FIG. A CTU is a block of a fixed size (for example, 64x64) that constitutes a slice, and is sometimes called a maximum coding unit (LCU: Large Coding Unit).

(Encoding tree unit)
As shown in (e) of FIG. 1, a set of data referred to by the image decoding device 31 in order to decode the encoding tree unit to be processed is defined. The coding tree unit is divided by recursive quadtree division. A tree-structured node obtained by recursive quadtree partitioning is referred to as a coding node (CN). An intermediate node of the quadtree is an encoding node, and the encoding tree unit itself is defined as the highest encoding node. The CTU includes a split flag (cu_split_flag), and when cu_split_flag is 1, it is split into four coding nodes CN. When cu_split_flag is 0, the coding node CN is not divided and has one coding unit (CU: Coding Unit) as a node. The encoding unit CU is a terminal node of the encoding node and is not further divided. The encoding unit CU is a basic unit of the encoding process.

  When the size of the coding tree unit CTU is 64x64 pixels, the size of the coding unit can be any of 64x64 pixels, 32x32 pixels, 16x16 pixels, and 8x8 pixels.

(Encoding unit)
As shown in (f) of FIG. 1, a set of data referred to by the image decoding device 31 in order to decode an encoding unit to be processed is defined. Specifically, the encoding unit includes a prediction tree, a conversion tree, and a CU header CUH. In the CU header, a prediction mode, a division method (PU division mode), and the like are defined.

  In the prediction tree, prediction information (a reference picture index, a motion vector, etc.) of each prediction unit (PU) obtained by dividing the coding unit into one or a plurality of parts is defined. In other words, the prediction unit is one or a plurality of non-overlapping areas constituting the encoding unit. The prediction tree includes one or a plurality of prediction units obtained by the above-described division. Hereinafter, a prediction unit obtained by further dividing the prediction unit is referred to as a “sub-block”. The sub block is composed of a plurality of pixels. When the sizes of the prediction unit and the sub-block are equal, the number of sub-blocks in the prediction unit is one. If the prediction unit is larger than the size of the sub-block, the prediction unit is divided into sub-blocks. For example, when the prediction unit is 8 × 8 and the sub-block is 4 × 4, the prediction unit is divided into four sub-blocks that are divided into two horizontally and two vertically.

  The prediction process may be performed for each prediction unit (sub-block).

  Broadly speaking, there are two types of division in the prediction tree: intra prediction and inter prediction. Intra prediction is prediction within the same picture, and inter prediction refers to prediction processing performed between different pictures (for example, between display times and between layer images).

  In the case of intra prediction, there are 2Nx2N (the same size as the coding unit) and NxN division methods.

Also, in the case of inter prediction, the division method is encoded by the PU division mode (part_mode) of the encoded data, 2Nx2N (the same size as the encoding unit), 2NxN, 2NxnU, 2NxnD, Nx2N, nLx2N, nRx2N, and NxN etc. 2NxN and Nx2N indicate 1: 1 symmetrical division,
2NxnU, 2NxnD and nLx2N, nRx2N show a 1: 3, 3: 1 asymmetric partitioning. The PUs included in the CU are expressed as PU0, PU1, PU2, and PU3 in this order.

  2A to 2H specifically illustrate the shape of the partition (the position of the boundary of the PU partition) in each PU partition mode. 2A shows a 2Nx2N partition, and FIGS. 2B, 2C, and 2D show 2NxN, 2NxnU, and 2NxnD partitions (horizontal partitions), respectively. (E), (f), and (g) show partitions (vertical partitions) in the case of Nx2N, nLx2N, and nRx2N, respectively, and (h) shows an NxN partition. The horizontal partition and the vertical partition are collectively referred to as a rectangular partition, and 2Nx2N and NxN are collectively referred to as a square partition.

  In the transform tree, the encoding unit is divided into one or a plurality of transform units, and the position and size of each transform unit are defined. In other words, a transform unit is one or more non-overlapping areas that make up a coding unit. The conversion tree includes one or a plurality of conversion units obtained by the above division.

  There are two types of division in the conversion tree: one in which an area having the same size as that of the encoding unit is allocated as a conversion unit, and the other in division by recursive quadtree division, similar to the above-described CU division.

  The conversion process is performed for each conversion unit.

(Prediction parameter)
A prediction image of a prediction unit (PU: Prediction Unit) is derived from a prediction parameter associated with the PU. The prediction parameters include a prediction parameter for intra prediction or a prediction parameter for inter prediction. Hereinafter, prediction parameters for inter prediction (inter prediction parameters) will be described. The inter prediction parameter includes prediction list use flags predFlagL0 and predFlagL1, reference picture indexes refIdxL0 and refIdxL1, and motion vectors mvL0 and mvL1. The prediction list use flags predFlagL0 and predFlagL1 are flags indicating whether or not reference picture lists called L0 list and L1 list are used, respectively, and a reference picture list corresponding to a value of 1 is used. In this specification, when “flag indicating whether or not it is XX” is described, when the flag is not 0 (for example, 1) is XX, 0 is not XX, and logical negation, logical product, etc. 1 is treated as true and 0 is treated as false (the same applies hereinafter). However, other values can be used as true values and false values in an actual apparatus or method.

(Reference picture list)
The reference picture list is a list including reference pictures stored in the reference picture memory 306.

(Merge prediction and AMVP prediction)
The prediction parameter decoding (encoding) method includes a merge prediction (merge) mode and an AMVP (Adaptive Motion Vector Prediction) mode. The merge flag merge_flag is a flag for identifying these. The merge prediction mode is a mode in which the prediction list use flag predFlagLX (or inter prediction identifier inter_pred_idc), the reference picture index refIdxLX, and the motion vector mvLX are not included in the encoded data and are derived from the prediction parameters of already processed neighboring PUs. The AMVP mode is a mode in which the inter prediction identifier inter_pred_idc, the reference picture index refIdxLX, and the motion vector mvLX are included in the encoded data. The motion vector mvLX is encoded as a prediction vector index mvp_LX_idx for identifying the prediction vector mvpLX and a difference vector mvdLX.

(Motion vector)
The motion vector mvLX indicates a shift amount between blocks on two different pictures. A prediction vector and a difference vector related to the motion vector mvLX are referred to as a prediction vector mvpLX and a difference vector mvdLX, respectively.

(Configuration of image decoding device)
Next, the configuration of the image decoding device 31 according to the present embodiment will be described. FIG. 4 is a schematic diagram illustrating a configuration of the image decoding device 31 according to the present embodiment. The image decoding device 31 includes an entropy decoding unit 301, a prediction parameter decoding unit (prediction image decoding device) 302, a loop filter 305, a reference picture memory 306, a prediction parameter memory 307, a prediction image generation unit (prediction image generation device) 308, and inversely. A quantization / inverse transform unit 311 and an adder 312 are included.

  The prediction parameter decoding unit 302 includes an inter prediction parameter decoding unit 303 and an intra prediction parameter decoding unit 304. The predicted image generation unit 308 includes an inter predicted image generation unit 309 and an intra predicted image generation unit 310.

  The entropy decoding unit 301 performs entropy decoding on an encoded stream Te input from the outside, and separates and decodes individual codes (syntax elements). The separated codes include prediction information for generating a prediction image and residual information for generating a difference image.

  The entropy decoding unit 301 outputs a part of the separated code to the prediction parameter decoding unit 302. Some of the separated codes are, for example, a prediction mode predMode, a PU partition mode part_mode, a merge flag merge_flag, a merge index merge_idx, an inter prediction identifier inter_pred_idc, a reference picture index refIdxLX, a prediction vector index mvp_LX_idx, and a difference vector mvdLX. Control of which code is decoded is performed based on an instruction from the prediction parameter decoding unit 302. The entropy decoding unit 301 outputs the quantized coefficient to the inverse quantization / inverse transform unit 311. In the coding process, this quantization coefficient is applied to the residual signal by DCT (Discrete Cosine Transform), DST (Discrete Sine Transform), KLT (Karyhnen Loeve Transform) It is a coefficient obtained by performing frequency conversion such as

  Based on the code input from the entropy decoding unit 301, the inter prediction parameter decoding unit 303 refers to the prediction parameter stored in the prediction parameter memory 307 and decodes the inter prediction parameter.

  The inter prediction parameter decoding unit 303 outputs the decoded inter prediction parameter to the prediction image generation unit 308 and stores it in the prediction parameter memory 307. Details of the inter prediction parameter decoding unit 303 will be described later.

  Based on the code input from the entropy decoding unit 301, the intra prediction parameter decoding unit 304 refers to the prediction parameter stored in the prediction parameter memory 307 and decodes the intra prediction parameter. The intra prediction parameter is a parameter used in a process of predicting a CU within one picture, for example, an intra prediction mode IntraPredMode. The intra prediction parameter decoding unit 304 outputs the decoded intra prediction parameter to the prediction image generation unit 308 and stores it in the prediction parameter memory 307.

  The intra prediction parameter decoding unit 304 may derive different intra prediction modes depending on the luminance and color difference. In this case, the intra prediction parameter decoding unit 304 decodes the luminance prediction mode IntraPredModeY as the luminance prediction parameter and the color difference prediction mode IntraPredModeC as the color difference prediction parameter. The luminance prediction mode IntraPredModeY is a 35 mode, and corresponds to planar prediction (0), DC prediction (1), and direction prediction (2 to 34). The color difference prediction mode IntraPredModeC uses any one of the planar prediction (0), the DC prediction (1), the direction prediction (2 to 34), and the LM mode (35). The intra prediction parameter decoding unit 304 decodes a flag indicating whether IntraPredModeC is the same mode as the luminance mode. If the flag indicates that the mode is the same as the luminance mode, IntraPredModeC is assigned to IntraPredModeC, and the flag indicates luminance. If the mode is different from the mode, planar prediction (0), DC prediction (1), direction prediction (2 to 34), and LM mode (35) may be decoded as IntraPredModeC.

  The loop filter 305 applies filters such as a deblocking filter, a sample adaptive offset (SAO), and an adaptive loop filter (ALF) to the decoded image of the CU generated by the adding unit 312.

  The reference picture memory 306 stores the decoded image of the CU generated by the adding unit 312 at a predetermined position for each decoding target picture and CU.

  The prediction parameter memory 307 stores the prediction parameter at a predetermined position for each decoding target picture and prediction unit (or sub-block, fixed-size block, pixel). Specifically, the prediction parameter memory 307 stores the inter prediction parameter decoded by the inter prediction parameter decoding unit 303, the intra prediction parameter decoded by the intra prediction parameter decoding unit 304, and the prediction mode predMode separated by the entropy decoding unit 301. . The stored inter prediction parameters include, for example, a prediction list utilization flag predFlagLX (inter prediction identifier inter_pred_idc), a reference picture index refIdxLX, and a motion vector mvLX.

  The prediction image generation unit 308 receives the prediction mode predMode input from the entropy decoding unit 301, and also receives prediction parameters from the prediction parameter decoding unit 302. Further, the predicted image generation unit 308 reads a reference picture from the reference picture memory 306. The prediction image generation unit 308 generates a prediction image of a PU or sub-block using the input prediction parameter and the read reference picture (reference picture block) in the prediction mode indicated by the prediction mode predMode.

  Here, when the prediction mode predMode indicates the inter prediction mode, the inter prediction image generation unit 309 uses the inter prediction parameter input from the inter prediction parameter decoding unit 303 and the read reference picture (reference picture block). To generate a prediction image of a PU or sub-block.

  For the reference picture list (L0 list or L1 list) for which the prediction list use flag predFlagLX is 1, the inter predicted image generation unit 309 uses the decoding target PU as a reference from the reference picture indicated by the reference picture index refIdxLX. The reference picture block at the position indicated by mvLX is read from the reference picture memory 306. The inter prediction image generation unit 309 performs prediction based on the read reference picture block to generate a prediction image of the PU. The inter prediction image generation unit 309 outputs the generated prediction image of the PU to the addition unit 312. Here, a reference picture block is a set of pixels on a reference picture (usually called a block because it is a rectangle), and is an area that is referred to in order to generate a predicted image of a PU or sub-block.

  When the prediction mode predMode indicates the intra prediction mode, the intra predicted image generation unit 310 performs intra prediction using the intra prediction parameter input from the intra prediction parameter decoding unit 304 and the read reference picture. Specifically, the intra predicted image generation unit 310 reads, from the reference picture memory 306, neighboring PUs that are pictures to be decoded and are in a predetermined range from the decoding target PUs among the PUs that have already been decoded. The predetermined range is, for example, one of the left, upper left, upper, and upper right adjacent PUs when the decoding target PU sequentially moves in the so-called raster scan order, and differs depending on the intra prediction mode. The raster scan order is an order in which each row is sequentially moved from the left end to the right end in each picture from the upper end to the lower end.

  The intra predicted image generation unit 310 performs prediction in the prediction mode indicated by the intra prediction mode IntraPredMode based on the read adjacent PU, and generates a predicted image of the PU. The intra predicted image generation unit 310 outputs the generated predicted image of the PU to the adding unit 312.

  When the intra prediction parameter decoding unit 304 derives an intra prediction mode different in luminance and color difference, the intra prediction image generation unit 310 performs planar prediction (0), DC prediction (1), direction according to the luminance prediction mode IntraPredModeY. The prediction image of the luminance PU is generated by any one of the predictions (2 to 34), and the planar prediction (0), the DC prediction (1), the direction prediction (2 to 34), and the LM mode according to the color difference prediction mode IntraPredModeC. A predicted image of the color difference PU is generated by any of (35).

  The inverse quantization / inverse transform unit 311 performs inverse quantization on the quantization coefficient input from the entropy decoding unit 301 to obtain a transform coefficient. The inverse quantization / inverse transform unit 311 performs inverse frequency transform such as inverse DCT, inverse DST, and inverse KLT on the obtained transform coefficient, and calculates a residual signal. The inverse quantization / inverse transform unit 311 outputs the calculated residual signal to the adder 312.

  The addition unit 312 adds the prediction image of the PU input from the inter prediction image generation unit 309 or the intra prediction image generation unit 310 and the residual signal input from the inverse quantization / inverse conversion unit 311 for each pixel, Generate a decoded PU image. The adding unit 312 stores the generated decoded image of the PU in the reference picture memory 306, and outputs a decoded image Td obtained by integrating the generated decoded image of the PU for each picture to the outside.

(Configuration of image encoding device)
Next, the configuration of the image encoding device 11 according to the present embodiment will be described. FIG. 3 is a block diagram illustrating a configuration of the image encoding device 11 according to the present embodiment. The image encoding device 11 includes a predicted image generation unit 101, a subtraction unit 102, a transform / quantization unit 103, an entropy encoding unit 104, an inverse quantization / inverse transform unit 105, an addition unit 106, a loop filter 107, and a prediction parameter memory. (Prediction parameter storage unit, frame memory) 108, reference picture memory (reference image storage unit, frame memory) 109, encoding parameter determination unit 110, and prediction parameter encoding unit 111. The prediction parameter encoding unit 111 includes an inter prediction parameter encoding unit 112 and an intra prediction parameter encoding unit 113.

  For each picture of the image T, the predicted image generation unit 101 generates a predicted image P of the prediction unit PU for each encoding unit CU that is an area obtained by dividing the picture. Here, the predicted image generation unit 101 reads a decoded block from the reference picture memory 109 based on the prediction parameter input from the prediction parameter encoding unit 111. The prediction parameter input from the prediction parameter encoding unit 111 is, for example, a motion vector in the case of inter prediction. The predicted image generation unit 101 reads a block at a position on the reference image indicated by the motion vector with the target PU as a starting point. In the case of intra prediction, the prediction parameter is, for example, an intra prediction mode. A pixel value of an adjacent PU used in the intra prediction mode is read from the reference picture memory 109, and a predicted image P of the PU is generated. The predicted image generation unit 101 generates a predicted image P of the PU using one prediction method among a plurality of prediction methods for the read reference picture block. The predicted image generation unit 101 outputs the generated predicted image P of the PU to the subtraction unit 102.

  Note that the predicted image generation unit 101 has the same operation as the predicted image generation unit 308 already described. For example, FIG. 5 is a schematic diagram illustrating a configuration of an inter predicted image generation unit 1011 included in the predicted image generation unit 101. The inter prediction image generation unit 1011 includes a motion compensation unit 10111 and a weight prediction unit 10112. Since the motion compensation unit 10111 and the weight prediction unit 10112 have the same configurations as the motion compensation unit 3091 and the weight prediction unit 3094 described above, description thereof is omitted here.

  The predicted image generation unit 101 generates a predicted image P of the PU based on the pixel value of the reference block read from the reference picture memory, using the parameter input from the prediction parameter encoding unit. The predicted image generated by the predicted image generation unit 101 is output to the subtraction unit 102 and the addition unit 106.

  The subtraction unit 102 subtracts the signal value of the predicted image P of the PU input from the predicted image generation unit 101 from the pixel value of the corresponding PU of the image T, and generates a residual signal. The subtraction unit 102 outputs the generated residual signal to the transform / quantization unit 103.

  The transformation / quantization unit 103 performs frequency transformation on the residual signal input from the subtraction unit 102 and calculates a transformation coefficient. The transform / quantization unit 103 quantizes the calculated transform coefficient to obtain a quantized coefficient. The transform / quantization unit 103 outputs the obtained quantization coefficient to the entropy coding unit 104 and the inverse quantization / inverse transform unit 105.

  The entropy encoding unit 104 receives the quantization coefficient from the transform / quantization unit 103 and the encoding parameter from the prediction parameter encoding unit 111. Examples of input encoding parameters include codes such as a reference picture index refIdxLX, a prediction vector index mvp_LX_idx, a difference vector mvdLX, a prediction mode predMode, and a merge index merge_idx.

  The entropy encoding unit 104 generates an encoded stream Te by entropy encoding the input quantization coefficient and encoding parameter, and outputs the generated encoded stream Te to the outside.

  The inverse quantization / inverse transform unit 105 inversely quantizes the quantization coefficient input from the transform / quantization unit 103 to obtain a transform coefficient. The inverse quantization / inverse transform unit 105 performs inverse frequency transform on the obtained transform coefficient to calculate a residual signal. The inverse quantization / inverse transform unit 105 outputs the calculated residual signal to the addition unit 106.

  The addition unit 106 adds the signal value of the prediction image P of the PU input from the prediction image generation unit 101 and the signal value of the residual signal input from the inverse quantization / inverse conversion unit 105 for each pixel, and performs decoding. Generate an image. The adding unit 106 stores the generated decoded image in the reference picture memory 109.

  The loop filter 107 performs a deblocking filter, a sample adaptive offset (SAO), and an adaptive loop filter (ALF) on the decoded image generated by the adding unit 106.

  The prediction parameter memory 108 stores the prediction parameter generated by the encoding parameter determination unit 110 at a predetermined position for each picture and CU to be encoded.

  The reference picture memory 109 stores the decoded image generated by the loop filter 107 at a predetermined position for each picture to be encoded and each CU.

  The encoding parameter determination unit 110 selects one set from among a plurality of sets of encoding parameters. The encoding parameter is a parameter to be encoded that is generated in association with the above-described prediction parameter or the prediction parameter. The predicted image generation unit 101 generates a predicted image P of the PU using each of these encoding parameter sets.

  The encoding parameter determination unit 110 calculates a cost value indicating the amount of information and the encoding error for each of the plurality of sets. The cost value is, for example, the sum of a code amount and a square error multiplied by a coefficient λ. The code amount is the information amount of the encoded stream Te obtained by entropy encoding the quantization error and the encoding parameter. The square error is the sum between pixels regarding the square value of the residual value of the residual signal calculated by the subtracting unit 102. The coefficient λ is a real number larger than a preset zero. The encoding parameter determination unit 110 selects a set of encoding parameters that minimizes the calculated cost value. As a result, the entropy encoding unit 104 outputs the selected set of encoding parameters to the outside as the encoded stream Te, and does not output the set of unselected encoding parameters. The encoding parameter determination unit 110 stores the determined encoding parameter in the prediction parameter memory 108.

  The prediction parameter encoding unit 111 derives a format for encoding from the parameters input from the encoding parameter determination unit 110 and outputs the format to the entropy encoding unit 104. Deriving the format for encoding is, for example, deriving a difference vector from a motion vector and a prediction vector. Also, the prediction parameter encoding unit 111 derives parameters necessary for generating a prediction image from the parameters input from the encoding parameter determination unit 110 and outputs the parameters to the prediction image generation unit 101. The parameter necessary for generating the predicted image is, for example, a motion vector in units of sub-blocks.

  The inter prediction parameter encoding unit 112 derives an inter prediction parameter such as a difference vector based on the prediction parameter input from the encoding parameter determination unit 110. The inter prediction parameter encoding unit 112 derives parameters necessary for generating a prediction image to be output to the prediction image generating unit 101, and an inter prediction parameter decoding unit 303 (see FIG. 4 and the like) derives an inter prediction parameter. Including the same configuration as that of The configuration of the inter prediction parameter encoding unit 112 will be described later.

  The intra prediction parameter encoding unit 113 derives a format (for example, MPM_idx, rem_intra_luma_pred_mode) for encoding from the intra prediction mode IntraPredMode input from the encoding parameter determination unit 110.

  In addition, a part of the image encoding device 11 and the image decoding device 31 in the above-described embodiment, for example, the entropy decoding unit 301, the prediction parameter decoding unit 302, the loop filter 305, the predicted image generation unit 308, the inverse quantization / inverse transformation. Unit 311, addition unit 312, predicted image generation unit 101, subtraction unit 102, transform / quantization unit 103, entropy encoding unit 104, inverse quantization / inverse transform unit 105, loop filter 107, encoding parameter determination unit 110, The prediction parameter encoding unit 111 may be realized by a computer. In that case, the program for realizing the control function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read by a computer system and executed. Here, the “computer system” is a computer system built in either the image encoding device 11 or the image decoding device 31 and includes hardware such as an OS and peripheral devices. The “computer-readable recording medium” refers to a storage device such as a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a hard disk built in a computer system. Furthermore, the “computer-readable recording medium” is a medium that dynamically holds a program for a short time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line, In such a case, a volatile memory inside a computer system serving as a server or a client may be included and a program that holds a program for a certain period of time. The program may be a program for realizing a part of the functions described above, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system.

(Synchronization example of deep learning network information)
Hereinafter, a configuration for synchronizing deep learning network information between image encoding devices and image decoding devices or between other image encoding devices will be described. For convenience of explanation, members having the same functions as those described above are denoted by the same reference numerals and description thereof is omitted.

  FIG. 6 is a schematic diagram illustrating the configuration of the image encoding device 11a according to the present example. As illustrated in FIG. 6, the image encoding device 11 a includes a CNN filter 32 instead of the loop filter 107 from the configuration illustrated in FIG. 3. The CNN filter 32 uses the decoded image generated by the adding unit 106 as an input image, performs one or a plurality of filter processes in its own neural network, and outputs output image data. In addition, the CNN filter 32 has a partially equivalent function as a CNN filter 34 described later.

  Further, the image encoding device 11a includes a neural network learning unit that executes deep learning for a neural network, that is, a neural network learning unit that learns a neural network. The image encoding device 11 a also has a function of acquiring deep learning network information from an external device and setting it to be used in the CNN filter 32. Here, the deep learning network information is data indicating the neural network itself in the CNN filter 32 and the CNN filter 34, or data defining the configuration of the neural network.

  In addition, in the image encoding device 11a and the image decoding device 31a that perform image transmission / reception, paired deep learning network information needs to be used. In other words, each device described above is required to use a common version of deep network information.

  FIG. 7 is a schematic diagram illustrating a configuration of the image decoding device 31a according to the present example. As illustrated in FIG. 7, the image decoding device 31 a includes a CNN filter 34 instead of the loop filter 305 from the configuration illustrated in FIG. 4.

  The CNN filter 34 uses the decoded image generated by the adding unit 312 as an input image, performs one or a plurality of filter processes in its own neural network, and outputs output image data. Further, the image decoding device 31 a has a function of acquiring deep learning network information from an external device and setting it to be used in the CNN filter 34. At this time, using the version information included in the encoded data, an appropriate version of neural network information is obtained from an external device.

  Here, the CNN is a convolution layer (a neuron has a spatial position and is connected only to an input close to the spatial position, and the weighting coefficient and bias / offset in the product-sum operation of the neuron are pictures. It is a generic name for neural networks having at least a layer that does not depend on the position in the network.

According to said structure, the image coding apparatus 11a can be made to learn the neural network which it has.
The weight coefficient is also called a kernel. In addition to the convolution layer, the CNN filter 34 is called a full connection layer (FCN). A neuron does not have a spatial position and is connected to all inputs, or a neuron called an LCN (Locally Connected Networks) layer. Is a configuration that has a spatial position and is connected only to an input close to the spatial position, but unlike CNN, can include a configuration that does not share a weighting factor or a bias.

  In the CNN filter 34, the input size to the convolution layer may be different from the output size from the convolution layer. That is, the CNN filter 34 can include a convolution layer in which the output size is smaller than the input size by making the amount of movement (step size) larger than 1 when moving the position where the convolution filter is applied. . In addition, a deconvolution layer (Deconvolution) in which the output size is larger than the input size can be included. The deconvolution layer may be called a transpose convolution layer (TransposeConvolution). The CNN filter 34 may include a pooling layer (Pooling), a dropout (DropOut) layer, and the like. The pooling layer is a layer that divides a large image into small windows, and obtains a representative value such as a maximum value or an average value according to each divided window, and the dropout layer has a fixed output (for example, output depending on the probability) 0) is a layer for adding randomness.

  FIG. 8 is a schematic diagram illustrating an example of a neural network included in the CNN filter 34. The CNN filter 34 includes a concat layer 51, one or more conv layers 52 provided in series, and an add layer 53.

  First, in the concat layer 51, the CNN filter 34 concatenates the decoded image generated by the adding unit 312 and the image having the encoding parameter as a pixel value. Here, in FIG. 8, recSamplesIn [] [] indicates the decoded image generated by the adding unit 312. Further, cuparam [] [] represents an image having a coding parameter as a pixel value. Note that the coding parameter may not be input to the CNN filter 34 and the CNN filter 34 may not include the concat layer 51.

  Subsequently, one or a plurality of filter processes referred to as a so-called convolution process are performed on one or a plurality of conv layers 52.

  Here, in the present embodiment, the conv layer 52 can include at least one of the following configurations.

(1) Conv (x): Configuration for performing filtering (convolution) (2) act (conv (x)): Activation after convolution (non-linear function such as sigmoid, tanh, relu, elu, selu, etc.) (3) batch_norm (act (conv (x))): Configuration that performs batch normalization (input range normalization) after convolution and activation (4) act (batch_norm (conv (x)) ): Configuration for performing batch normalization (normalization of input range) between convolution and activation (5) pooling: Configuration for compressing information and leveling spatial changes between conv layers Next, add layer 53 Adds the decoded image generated by the adding unit 312 and the image on which one or more filter processes have been performed for each pixel, and outputs the result as the output of the CNN filter 34. Here, recSamplesOut [] [] in FIG. 8 indicates the output of the CNN filter 34.

  The entropy decoding unit 301 according to this example also functions as a neural network specifying unit that specifies a neural network with reference to identification information included in the encoded data. In the configuration illustrated in FIG. 7, the member group excluding the entropy decoding unit 301 corresponds to a decoded image generation unit 33 that performs a decoded image generation process including a filter process. The decoded image generation unit 33 has a function of acquiring deep learning network information from an external device and setting it to be used in the CNN filter 34.

  FIG. 9 is a diagram showing a deep learning network synchronization system (image encoding / video decoding system) according to the present example. Here, the network management device 71 stores the deep learning network information used inside the individual image encoding device 11a and the image decoding device 31a, and sends it to the image encoding device 11a or the image decoding device 31a as necessary. The server to distribute.

  Further, deep learning is performed inside each image encoding device 11a, and deep learning network information is generated inside the encoding device. Then, the network management device 71 updates the deep learning network information by aggregating the deep learning network information therein, and manages the information as a pair with the deep learning identification information. Here, the deep learning identification information is an identifier uniquely assigned to the deep learning network information held by the network management device 71.

  Next, the operation in which the network management apparatus 71 updates the deep learning identification information will be described with reference to FIG. The deep learning network synchronization system shown in FIG. 10 shows an example in which two image encoding devices 11a are included.

  In FIG. 1A, each image encoding device 11 a acquires a variable (deep learning network information) from the network management device 71.

  Subsequently, in FIG. 2B, the image encoding device 11a calculates the gradient calculated from the learning data according to the defined model for each acquired variable. Note that “loss” in FIG. 10 indicates processing using a loss function when calculating a gradient.

  Subsequently, in FIG. 3 (3), the network management device 71 receives the calculation result of the gradient from each encoding device, and calculates the average value.

  Subsequently, in FIG. 4 (4), the network management device 71 updates each variable based on the averaged gradient, and stores it as a pair with identification information (deep learning identification information). These algorithms are general distributed learning algorithms, but are not limited thereto. Further, the above-described algorithm means that the neural network used for deep learning may be learned in a distributed manner in the plurality of image encoding devices 11a.

  Next, processing in each image encoding device 11a will be described. The image encoding device 11a acquires the deep learning network information and the deep learning identification information from the network management device 71. Subsequently, the image encoding device 11a generates encoded data using the acquired deep learning network information, and transmits the encoded data and the deep learning identification information to the image decoding device 31a.

  Note that the timing at which the image encoding device 11a downloads the deep learning network information from the network management device 71 is freely determined by the user application. For example, when a predetermined time elapses, the network management device 71 checks whether new deep learning network information has been generated, and downloads any new information. At this time, when the deep learning network information is exchanged in a compressed form, a compression process (not shown) is performed at the transmission source, and a decompression process (not shown) is performed at the reception destination.

  The deep learning identification information is a numerical value indicating version information, for example. When the image encoding device 11a has a plurality of deep learning networks, for example, in addition to the version number, a method of combining processing functions realized by the deep learning network as an identification name is also conceivable. For example, since the neural network shown in this embodiment has a function of “loop filter”, the identification name of the loop filter is used. In this way, although there is no specific description in the present embodiment, appropriate deep learning network information can be efficiently managed when a plurality of neural networks are included in the encoding device and decoding device.

  Subsequently, the image encoding device 11a generates encoded data using the acquired deep learning network information, and transmits the encoded data and the deep learning identification information to the image decoding device 31a. As a method of storing the deep learning identification information in the encoded data, a method of including it in a part of management information such as SPS or PPS in the encoded data is conceivable.

  The image decoding device 31a compares the deep learning identification information included in the encoded data with the deep learning identification information included in the image decoding device 31a. If both are different, the corresponding deep learning network information is requested from the network management device 71 and downloaded and used. Similar to the image encoding device 11a, when the deep learning network information is exchanged in a compressed form, a compression process (not shown) is performed at the transmission source, and a decompression process (not shown) is performed at the reception destination. Subsequently, the image decoding device 31a performs a decoding process using the deep learning network information corresponding to the deep learning identification information included in the encoded data.

  As described above, in the image encoding device 11a that generates encoded data according to this example, an encoding unit (entropy) that generates encoded data by encoding an image that has been filtered using a neural network. The encoding unit 104 includes identification information for identifying the neural network from other neural networks in the encoded data.

  According to said structure, the encoding apparatus 11a which produces | generates the encoding stream which can identify the neural network which the image decoding apparatus itself 31a should use is realizable.

  Further, as described above, the image decoding device 31a that decodes the encoded data according to this example refers to the neural network specifying unit (entropy decoding unit) that specifies the neural network with reference to the identification information included in the encoded data. 301 and a decoded image generation unit 33 that performs a decoded image generation process including a filter process using the identified neural network.

  According to said structure, the image decoding apparatus 31a can specify the neural network which should be used, and can use it for a decoded image generation process.

  Further, as described above, in the image coding system (deep learning network synchronization system) according to the present example, each of the plurality of image coding devices 11a encodes the filtered image using a neural network. Thus, an encoding unit 104 that generates encoded data is provided, and the neural network is learned in a distributed manner in the plurality of image encoding devices 11a.

  According to the above configuration, an image encoding system capable of learning a neural network in a distributed manner can be realized.

  Up to this point, the configuration example with one network management device 71 has been described. However, the deep learning network synchronization system may include a plurality of network management devices 71. For example, as shown in FIG. 11, the deep learning network synchronization system may include a second network management device 71 ′ that further bundles a plurality of network management devices. In the above configuration, the operation of synchronizing the deep learning network information is performed by causing the network management device 71 to operate as the previous image encoding device 11a and the second network management device 71 ′ to operate as the previous network management device 71. Hierarchical management is possible.

  In the case of a configuration in which a plurality of network management devices 71 are provided, it is necessary for the image encoding device 11a and the image decoding device 31a to identify which server stores the target deep learning network information. Here, the deep learning identification information may be managed using an address and mask information such as an IP address so that the hierarchy and version indicating the management subject of the deep learning network information are uniquely determined. An example is shown in FIG. In this case, the entire deep learning identification information is represented by 24 bits. For example, when the network management device 71 uses a mask of 0.0.255, the rightmost 8 bits can be identified, and when the second network management device 71 ′ uses a mask of 0.255.0, the center 8 bits can be identified. .

  Furthermore, when the result of using the mask is 0, if it is set that the network of that layer is not used, if a non-zero value is output with the mask of 0.0.255, the network management device 71 sets the target. It can be seen that deep learning network information is managed. When a value other than zero is output at 0.255.0, it is understood that the target deep learning network information is managed by the second network management device 71 '. As described above, the image encoding device 11a and the image decoding device 31a use the address information and a plurality of masks to identify which network management server can acquire the target deep learning network information. It is also possible.

  Moreover, you may implement | achieve part or all of the image coding apparatus 11 in the embodiment mentioned above, and the image decoding apparatus 31 as integrated circuits, such as LSI (Large Scale Integration). Each functional block of the image encoding device 11 and the image decoding device 31 may be individually made into a processor, or a part or all of them may be integrated into a processor. Further, the method of circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. Further, in the case where an integrated circuit technology that replaces LSI appears due to progress in semiconductor technology, an integrated circuit based on the technology may be used.

  As described above, the embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to the above, and various design changes and the like can be made without departing from the scope of the present invention. It is possible to

[Application example]
The image encoding device 11 and the image decoding device 31 described above can be used by being mounted on various devices that perform transmission, reception, recording, and reproduction of moving images. The moving image may be a natural moving image captured by a camera or the like, or an artificial moving image (including CG and GUI) generated by a computer or the like.

  First, it will be described with reference to FIG. 13 that the above-described image encoding device 11 and image decoding device 31 can be used for transmission and reception of moving images.

  FIG. 13A is a block diagram illustrating a configuration of a transmission device PROD_A in which the image encoding device 11 is mounted. As illustrated in FIG. 13A, the transmission apparatus PROD_A modulates a carrier wave with an encoding unit PROD_A1 that obtains encoded data by encoding a moving image, and with the encoded data obtained by the encoding unit PROD_A1. Thus, a modulation unit PROD_A2 that obtains a modulation signal and a transmission unit PROD_A3 that transmits the modulation signal obtained by the modulation unit PROD_A2 are provided. The above-described image encoding device 11 is used as the encoding unit PROD_A1.

  Transmission device PROD_A, as a source of moving images to be input to the encoding unit PROD_A1, a camera PROD_A4 that captures moving images, a recording medium PROD_A5 that records moving images, an input terminal PROD_A6 for inputting moving images from the outside, and An image processing unit A7 that generates or processes an image may be further provided. FIG. 13A illustrates a configuration in which the transmission apparatus PROD_A includes all of these, but a part of the configuration may be omitted.

  Note that the recording medium PROD_A5 may be a recording of a non-encoded moving image, or a recording of a moving image encoded by a recording encoding scheme different from the transmission encoding scheme. It may be a thing. In the latter case, a decoding unit (not shown) for decoding the encoded data read from the recording medium PROD_A5 in accordance with the recording encoding method may be interposed between the recording medium PROD_A5 and the encoding unit PROD_A1.

  FIG. 13B is a block diagram illustrating a configuration of the receiving device PROD_B in which the image decoding device 31 is mounted. As shown in FIG. 13B, the receiving device PROD_B includes a receiving unit PROD_B1 that receives a modulated signal, a demodulating unit PROD_B2 that obtains encoded data by demodulating the modulated signal received by the receiving unit PROD_B1, and a demodulator A decoding unit PROD_B3 that obtains a moving image by decoding the encoded data obtained by the unit PROD_B2. The above-described image decoding device 31 is used as the decoding unit PROD_B3.

  The receiving device PROD_B is a display destination PROD_B4 for displaying a moving image, a recording medium PROD_B5 for recording a moving image, and an output terminal for outputting the moving image to the outside as a supply destination of the moving image output by the decoding unit PROD_B3 PROD_B6 may be further provided. In FIG. 13B, a configuration in which all of these are provided in the receiving device PROD_B is illustrated, but a part may be omitted.

  Note that the recording medium PROD_B5 may be used for recording a non-encoded moving image, or is encoded using a recording encoding method different from the transmission encoding method. May be. In the latter case, an encoding unit (not shown) for encoding the moving image acquired from the decoding unit PROD_B3 according to the recording encoding method may be interposed between the decoding unit PROD_B3 and the recording medium PROD_B5.

  Note that the transmission medium for transmitting the modulation signal may be wireless or wired. Further, the transmission mode for transmitting the modulated signal may be broadcasting (here, a transmission mode in which the transmission destination is not specified in advance) or communication (here, transmission in which the transmission destination is specified in advance). Refers to the embodiment). That is, the transmission of the modulation signal may be realized by any of wireless broadcasting, wired broadcasting, wireless communication, and wired communication.

  For example, a terrestrial digital broadcast broadcasting station (such as broadcasting equipment) / receiving station (such as a television receiver) is an example of a transmitting device PROD_A / receiving device PROD_B that transmits and receives a modulated signal by wireless broadcasting. A broadcasting station (such as broadcasting equipment) / receiving station (such as a television receiver) of cable television broadcasting is an example of a transmitting device PROD_A / receiving device PROD_B that transmits and receives a modulated signal by cable broadcasting.

  Also, a server (workstation, etc.) / Client (television receiver, personal computer, smartphone, etc.) such as a VOD (Video On Demand) service or a video sharing service using the Internet is a transmission device that transmits and receives modulated signals by communication. This is an example of PROD_A / receiving device PROD_B (normally, either a wireless or wired transmission medium is used in a LAN, and a wired transmission medium is used in a WAN). Here, the personal computer includes a desktop PC, a laptop PC, and a tablet PC. The smartphone also includes a multi-function mobile phone terminal.

  Note that the client of the video sharing service has a function of encoding a moving image captured by a camera and uploading it to the server in addition to a function of decoding the encoded data downloaded from the server and displaying it on the display. That is, the client of the video sharing service functions as both the transmission device PROD_A and the reception device PROD_B.

  Next, the fact that the above-described image encoding device 11 and image decoding device 31 can be used for recording and reproduction of moving images will be described with reference to FIG.

  FIG. 14A is a block diagram illustrating a configuration of a recording apparatus PROD_C in which the above-described image encoding device 11 is mounted. As shown in FIG. 14 (a), the recording apparatus PROD_C includes an encoding unit PROD_C1 that obtains encoded data by encoding a moving image, and the encoded data obtained by the encoding unit PROD_C1 on a recording medium PROD_M. A writing unit PROD_C2 for writing. The above-described image encoding device 11 is used as the encoding unit PROD_C1.

  The recording medium PROD_M may be of a type built into the recording device PROD_C, such as (1) HDD (Hard Disk Drive) or SSD (Solid State Drive), or (2) SD memory. It may be of the type connected to the recording device PROD_C, such as a card or USB (Universal Serial Bus) flash memory, or (3) DVD (Digital Versatile Disc) or BD (Blu-ray Disc: registration) Or a drive device (not shown) built in the recording device PROD_C.

  In addition, the recording device PROD_C is a camera PROD_C3 that captures moving images as a source of moving images to be input to the encoding unit PROD_C1, an input terminal PROD_C4 for inputting moving images from the outside, and a reception for receiving moving images A unit PROD_C5 and an image processing unit PROD_C6 for generating or processing an image may be further provided. FIG. 14A illustrates a configuration in which the recording apparatus PROD_C includes all of these, but some of them may be omitted.

  The receiving unit PROD_C5 may receive a non-encoded moving image, or may receive encoded data encoded by a transmission encoding scheme different from the recording encoding scheme. You may do. In the latter case, a transmission decoding unit (not shown) that decodes encoded data encoded by the transmission encoding method may be interposed between the reception unit PROD_C5 and the encoding unit PROD_C1.

  Examples of such a recording device PROD_C include a DVD recorder, a BD recorder, an HDD (Hard Disk Drive) recorder, and the like (in this case, the input terminal PROD_C4 or the receiving unit PROD_C5 is a main source of moving images). . In addition, a camcorder (in this case, the camera PROD_C3 is a main source of moving images), a personal computer (in this case, the receiving unit PROD_C5 or the image processing unit C6 is a main source of moving images), a smartphone (this In this case, the camera PROD_C3 or the reception unit PROD_C5 is a main source of moving images), and the like is also an example of such a recording apparatus PROD_C.

  FIG. 14B is a block showing the configuration of the playback device PROD_D in which the above-described image decoding device 31 is mounted. As shown in FIG. 14B, the playback device PROD_D reads a moving image by decoding a read unit PROD_D1 that reads encoded data written on the recording medium PROD_M and a read unit PROD_D1 that reads the encoded data. And a decoding unit PROD_D2 to obtain. The above-described image decoding device 31 is used as the decoding unit PROD_D2.

  The recording medium PROD_M may be of the type built into the playback device PROD_D, such as (1) HDD or SSD, or (2) such as an SD memory card or USB flash memory. It may be of the type connected to the playback device PROD_D, or (3) may be loaded into a drive device (not shown) built in the playback device PROD_D, such as a DVD or BD. Good.

  In addition, the playback device PROD_D has a display unit PROD_D3 that displays a moving image as a supply destination of the moving image output by the decoding unit PROD_D2, an output terminal PROD_D4 that outputs the moving image to the outside, and a transmission unit that transmits the moving image. PROD_D5 may be further provided. FIG. 14B illustrates a configuration in which the playback apparatus PROD_D includes all of these, but some of them may be omitted.

  The transmission unit PROD_D5 may transmit a non-encoded moving image, or transmits encoded data encoded by a transmission encoding scheme different from the recording encoding scheme. You may do. In the latter case, it is preferable to interpose an encoding unit (not shown) that encodes a moving image using a transmission encoding method between the decoding unit PROD_D2 and the transmission unit PROD_D5.

  Examples of such a playback device PROD_D include a DVD player, a BD player, and an HDD player (in this case, an output terminal PROD_D4 to which a television receiver or the like is connected is a main moving image supply destination). . In addition, a television receiver (in this case, the display PROD_D3 is a main supply destination of moving images), a digital signage (also referred to as an electronic signboard or an electronic bulletin board), and the display PROD_D3 or the transmission unit PROD_D5 is the main supply of moving images. Desktop PC (in this case, output terminal PROD_D4 or transmission unit PROD_D5 is the main video source), laptop or tablet PC (in this case, display PROD_D3 or transmission unit PROD_D5 is video) A smartphone (which is a main image supply destination), a smartphone (in this case, the display PROD_D3 or the transmission unit PROD_D5 is a main moving image supply destination), and the like are also examples of such a playback device PROD_D.

(Hardware implementation and software implementation)
Each block of the image decoding device 31 and the image encoding device 11 described above may be realized in hardware by a logic circuit formed on an integrated circuit (IC chip), or may be a CPU (Central Processing Unit). You may implement | achieve by software using.

  In the latter case, each device includes a CPU that executes instructions of a program that realizes each function, a ROM (Read Only Memory) that stores the program, a RAM (Random Access Memory) that expands the program, the program, and various types A storage device (recording medium) such as a memory for storing data is provided. The object of the embodiment of the present invention is a record in which the program code (execution format program, intermediate code program, source program) of the control program for each of the above devices, which is software that realizes the functions described above, is recorded so as to be readable by a computer. This can also be achieved by supplying a medium to each of the above devices, and reading and executing the program code recorded on the recording medium by the computer (or CPU or MPU).

  Examples of the recording medium include magnetic tapes and cassette tapes, magnetic disks such as floppy (registered trademark) disks / hard disks, CD-ROM (Compact Disc Read-Only Memory) / MO disks (Magneto-Optical discs), and the like. ) / MD (Mini Disc) / DVD (Digital Versatile Disc) / CD-R (CD Recordable) / Blu-ray Disc (registered trademark) and other optical discs, IC cards (including memory cards) / Cards such as optical cards, mask ROM / EPROM (Erasable Programmable Read-Only Memory) / EEPROM (Electrically Erasable and Programmable Read-Only Memory: registered trademark) / Semiconductor memories such as flash ROM, or PLD (Programmable logic device) ) Or FPGA (Field Programmable Gate Array).

  Further, each of the above devices may be configured to be connectable to a communication network, and the program code may be supplied via the communication network. The communication network is not particularly limited as long as it can transmit the program code. For example, the Internet, Intranet, Extranet, LAN (Local Area Network), ISDN (Integrated Services Digital Network), VAN (Value-Added Network), CATV (Community Antenna television / Cable Television) communication network, Virtual Private Network (Virtual Private Network) Network), telephone line network, mobile communication network, satellite communication network, and the like. The transmission medium constituting the communication network may be any medium that can transmit the program code, and is not limited to a specific configuration or type. For example, IEEE (Institute of Electrical and Electronic Engineers) 1394, USB, power line carrier, cable TV line, telephone line, ADSL (Asymmetric Digital Subscriber Line) line, etc. wired, such as IrDA (Infrared Data Association) or remote control , BlueTooth (registered trademark), IEEE802.11 wireless, HDR (High Data Rate), NFC (Near Field Communication), DLNA (Digital Living Network Alliance: registered trademark), mobile phone network, satellite line, terrestrial digital broadcasting network, etc. It can also be used wirelessly. The embodiment of the present invention can also be realized in the form of a computer data signal embedded in a carrier wave in which the program code is embodied by electronic transmission.

  The embodiments of the present invention are not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. That is, embodiments obtained by combining technical means appropriately modified within the scope of the claims are also included in the technical scope of the present invention.

  Embodiments of the present invention can be preferably applied to an image decoding apparatus that decodes encoded data in which image data is encoded, and an image encoding apparatus that generates encoded data in which image data is encoded. it can. Further, the present invention can be suitably applied to the data structure of encoded data generated by an image encoding device and referenced by the image decoding device.

DESCRIPTION OF SYMBOLS 1 Image transmission system 11, 11a Image coding apparatus 21 Network 31, 31a Image decoding apparatus 32, 34 CNN filter 33 Decoded image generation part 41 Image display apparatus 71 Network management apparatus 71 '2nd network management apparatus 101,308 Predictive image Generation unit 102 Subtraction unit 103 Quantization unit 104 Entropy encoding unit (encoding unit)
105, 311 Inverse transform unit 106, 312 Adder unit 107, 305 Loop filter 108, 307 Prediction parameter memory 109, 306 Reference picture memory 110 Coding parameter determination unit 111 Prediction parameter coding unit 112 Inter prediction parameter coding unit 113 Intra prediction Parameter encoding unit 301 Entropy decoding unit (neural network specifying unit)
302 Prediction Parameter Decoding Unit 303 Inter Prediction Parameter Decoding Unit 304 Intra Prediction Parameter Decoding Units 309 and 1011 Inter Prediction Image Generation Unit 310 Intra Prediction Image Generation Units 10111 and 3091 Compensation Units 10112 and 3094 Prediction Unit Te Encoded Stream

Claims (4)

In an image encoding device that generates encoded data,
An encoding unit that generates encoded data by encoding the filtered image using a neural network;
The image encoding apparatus, wherein the encoding unit includes identification information for identifying the neural network from another neural network in the encoded data.   The image coding apparatus according to claim 1, further comprising a neural network learning unit that learns the neural network. In an image decoding device for decoding encoded data,
A neural network specifying unit for specifying a neural network with reference to the identification information included in the encoded data;
An image decoding apparatus comprising: a decoded image generation unit that performs a decoded image generation process including a filter process using the identified neural network. An image encoding system including a plurality of image encoding devices,
Each of the plurality of image encoding devices includes:
An encoding unit that generates encoded data by encoding the filtered image using a neural network;
The neural network is learned in a distributed manner in the plurality of image encoding devices.

Images