WO2023055141A1 - 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 - Google Patents
피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 Download PDFInfo
- Publication number
- WO2023055141A1 WO2023055141A1 PCT/KR2022/014686 KR2022014686W WO2023055141A1 WO 2023055141 A1 WO2023055141 A1 WO 2023055141A1 KR 2022014686 W KR2022014686 W KR 2022014686W WO 2023055141 A1 WO2023055141 A1 WO 2023055141A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- feature
- information
- filtering
- feature map
- feature information
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 168
- 238000001914 filtration Methods 0.000 claims abstract description 147
- 230000001131 transforming effect Effects 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 description 31
- 238000013139 quantization Methods 0.000 description 30
- 230000009466 transformation Effects 0.000 description 29
- 239000000523 sample Substances 0.000 description 24
- 238000000605 extraction Methods 0.000 description 23
- 238000010586 diagram Methods 0.000 description 22
- 238000012545 processing Methods 0.000 description 21
- 239000013598 vector Substances 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 17
- 230000005540 biological transmission Effects 0.000 description 14
- 230000002123 temporal effect Effects 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 11
- 230000006835 compression Effects 0.000 description 9
- 238000007906 compression Methods 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 8
- 241000023320 Luma <angiosperm> Species 0.000 description 7
- 239000011449 brick Substances 0.000 description 7
- 239000000284 extract Substances 0.000 description 7
- OSWPMRLSEDHDFF-UHFFFAOYSA-N methyl salicylate Chemical compound COC(=O)C1=CC=CC=C1O OSWPMRLSEDHDFF-UHFFFAOYSA-N 0.000 description 7
- 230000003044 adaptive effect Effects 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- YLZOPXRUQYQQID-UHFFFAOYSA-N 3-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-yl)-1-[4-[2-[[3-(trifluoromethoxy)phenyl]methylamino]pyrimidin-5-yl]piperazin-1-yl]propan-1-one Chemical compound N1N=NC=2CN(CCC=21)CCC(=O)N1CCN(CC1)C=1C=NC(=NC=1)NCC1=CC(=CC=C1)OC(F)(F)F YLZOPXRUQYQQID-UHFFFAOYSA-N 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000009877 rendering Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000013074 reference sample Substances 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000010454 slate Substances 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/89—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving methods or arrangements for detection of transmission errors at the decoder
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/117—Filters, e.g. for pre-processing or post-processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/124—Quantisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/184—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/70—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/80—Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
- H04N19/82—Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
Definitions
- the present disclosure relates to a feature encoding/decoding method and apparatus, and more particularly, to a feature encoding/decoding method and apparatus for compensating an error due to feature point dimensionality reduction, and a bitstream generated by the feature encoding method/device of the present disclosure. It relates to a recording medium storing the.
- An object of the present disclosure is to provide a feature encoding/decoding method and apparatus having improved encoding/decoding efficiency.
- an object of the present disclosure is to provide a feature encoding/decoding method and apparatus for compensating for an error due to feature point dimensionality reduction.
- an object of the present disclosure is to provide a feature encoding/decoding method and apparatus for applying a filter to minimize a difference between a feature map before applying feature dimensionality reduction and a feature map reconstructed to an original dimension.
- an object of the present disclosure is to provide a feature encoding/decoding method and apparatus for transmitting information related to the filter.
- an object of the present disclosure is to provide a method or device for transmitting a bitstream generated by a feature encoding method or device according to the present disclosure.
- an object of the present disclosure is to provide a recording medium storing a bitstream generated by a feature encoding method or apparatus according to the present disclosure.
- an object of the present disclosure is to provide a recording medium storing a bitstream received and decoded by a feature decoding apparatus according to the present disclosure and used for restoring a feature.
- a feature decoding method includes obtaining first feature information and filtering information for the first feature information from a bitstream; inversely transforming the first feature information; and deriving second feature information for the inversely transformed first feature information based on the filtering information.
- a feature encoding method includes deriving transformed feature information based on feature information extracted from an image; deriving inverse transformed feature information based on the transformed feature information; and deriving filtering information based on the inverse transformed feature information.
- a recording medium may store a bitstream generated by a feature encoding method or a feature encoding apparatus according to the present disclosure.
- a bitstream transmission method may transmit a bitstream generated by a feature encoding method or a feature encoding apparatus according to the present disclosure to a feature decoding apparatus.
- a method and apparatus for encoding/decoding feature information with improved encoding/decoding efficiency may be provided.
- FIG. 1 is a diagram schematically illustrating a VCM system to which embodiments of the present disclosure may be applied.
- FIG. 2 is a diagram schematically illustrating a VCM pipeline structure to which embodiments of the present disclosure may be applied.
- FIG. 3 is a diagram schematically illustrating an image/video encoder to which embodiments of the present disclosure may be applied.
- FIG. 4 is a diagram schematically illustrating an image/video decoder to which embodiments of the present disclosure may be applied.
- FIG. 5 is a flowchart schematically illustrating a feature/feature map encoding procedure to which embodiments of the present disclosure may be applied.
- FIG. 6 is a flowchart schematically illustrating a feature/feature map decoding procedure to which embodiments of the present disclosure may be applied.
- FIG. 7 is a diagram illustrating an example of a feature extraction and restoration method to which embodiments of the present disclosure may be applied.
- FIG. 8 is a diagram illustrating an example of a feature extraction method using a feature extraction network.
- 9 is a diagram illustrating an example of extracted features.
- 10 is a diagram illustrating an example of the size of an extracted feature set.
- FIG. 11 is a diagram illustrating an example of a feature extraction and restoration method to which embodiments of the present disclosure may be applied.
- FIG. 12 is a flowchart illustrating a feature encoding method according to an embodiment of the present disclosure.
- FIG. 13 is a diagram illustrating an example of a type of filter that can be used for error compensation.
- FIG. 14 is a flowchart illustrating a feature decoding method according to an embodiment of the present disclosure.
- 15 and 16 are flowcharts illustrating feature encoding methods according to an embodiment of the present disclosure.
- 17 is a flowchart illustrating a feature decoding method according to an embodiment of the present disclosure.
- FIG. 18 is a flowchart illustrating a feature encoding method according to an embodiment of the present disclosure.
- 19 is a flowchart illustrating a feature decoding method according to an embodiment of the present disclosure.
- FIG. 20 is a flowchart illustrating a feature encoding method according to an embodiment of the present disclosure.
- 21 is a flowchart illustrating a feature decoding method according to an embodiment of the present disclosure.
- FIG. 22 is a diagram illustrating an example of a content streaming system to which embodiments of the present disclosure may be applied.
- FIG. 23 is a diagram illustrating another example of a content streaming system to which embodiments of the present disclosure may be applied.
- first and second are used only for the purpose of distinguishing one element from another, and do not limit the order or importance of elements unless otherwise specified. Accordingly, within the scope of the present disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and similarly, a second component in one embodiment may be referred to as a first component in another embodiment. can also be called
- components that are distinguished from each other are intended to clearly explain each characteristic, and do not necessarily mean that the components are separated. That is, a plurality of components may be integrated to form a single hardware or software unit, or a single component may be distributed to form a plurality of hardware or software units. Accordingly, even such integrated or distributed embodiments are included in the scope of the present disclosure, even if not mentioned separately.
- components described in various embodiments do not necessarily mean essential components, and some may be optional components. Accordingly, an embodiment comprising a subset of elements described in one embodiment is also included in the scope of the present disclosure. In addition, embodiments including other components in addition to the components described in various embodiments are also included in the scope of the present disclosure.
- the present disclosure relates to encoding and decoding of an image, and terms used in the present disclosure may have common meanings commonly used in the technical field to which the present disclosure belongs unless newly defined in the present disclosure.
- the present disclosure may be applied to a method disclosed in a Versatile Video Coding (VVC) standard and/or a Video Coding for Machines (VCM) standard.
- VVC Versatile Video Coding
- VCM Video Coding for Machines
- EVC essential video coding
- AV1 AOMedia Video 1
- AVS2 2nd generation of audio video coding standard
- next-generation video/video coding standard e.g., H.267 or H.268, etc.
- video refers to a series of It may mean a set of images.
- An “image” may be information generated by artificial intelligence (AI).
- AI artificial intelligence
- Input information used in the process of performing a series of tasks by AI, information generated during information processing, and output information can be used as images.
- a “picture” generally means a unit representing one image in a specific time period, and a slice/tile is a coding unit constituting a part of a picture in coding.
- One picture may consist of one or more slices/tiles.
- a slice/tile may include one or more coding tree units (CTUs).
- CTUs coding tree units
- the CTU may be divided into one or more CUs.
- a tile is a rectangular area existing in a specific tile row and specific tile column in a picture, and may be composed of a plurality of CTUs.
- a tile column may be defined as a rectangular area of CTUs, has the same height as the picture height, and may have a width specified by a syntax element signaled from a bitstream part such as a picture parameter set.
- a tile row may be defined as a rectangular area of CTUs, has the same width as the width of a picture, and may have a height specified by a syntax element signaled from a bitstream part such as a picture parameter set.
- Tile scan is a method of specifying a predetermined contiguous ordering of CTUs dividing a picture.
- CTUs may be sequentially assigned an order according to a CTU raster scan within a tile, and tiles within a picture may be sequentially assigned an order according to a raster scan order of tiles of the picture.
- a slice may contain an integer number of complete tiles, or may contain a contiguous integer number of complete CTU rows within one tile of one picture.
- a slice may be contained exclusively in one single NAL unit.
- One picture may be composed of one or more tile groups.
- One tile group may include one or more tiles.
- a brick may represent a rectangular area of CTU rows within a tile in a picture.
- One tile may include one or more bricks.
- a brick may represent a rectangular area of CTU rows in a tile.
- One tile may be divided into a plurality of bricks, and each brick may include one or more CTU rows belonging to the tile. Tiles that are not divided into multiple bricks can also be treated as bricks.
- pixel or “pel” may mean a minimum unit constituting one picture (or image).
- sample may be used as a term corresponding to a pixel.
- a sample may generally represent a pixel or a pixel value, may represent only a pixel/pixel value of a luma component, or only a pixel/pixel value of a chroma component.
- a pixel/pixel value is independent information of each component or a pixel of a component generated through combination, synthesis, or analysis when there is a picture composed of a set of components having different characteristics and meanings.
- / can also indicate a pixel value.
- a pixel/pixel value For example, in the RGB input, only the pixel/pixel value of R may be displayed, only the pixel/pixel value of G may be displayed, or only the pixel/pixel value of B may be displayed.
- only pixel/pixel values of a Luma component synthesized using R, G, and B components may be indicated.
- only pixels/pixel values of images and information extracted from R, G, and B components through analysis may be indicated.
- a “unit” may represent a basic unit of image processing.
- a unit may include at least one of a specific region of a picture and information related to the region.
- One unit may include one luma block and two chroma (e.g., Cb, Cr) blocks.
- Unit may be used interchangeably with terms such as "sample array", "block” or "area” depending on the case.
- an MxN block may include samples (or a sample array) or a set (or array) of transform coefficients consisting of M columns and N rows.
- the unit may represent a basic unit containing information for performing a specific task.
- “current block” may mean one of “current coding block”, “current coding unit”, “encoding object block”, “decoding object block”, or “processing object block”.
- “current block” may mean “current prediction block” or “prediction target block”.
- transform inverse transform
- quantization inverse quantization
- “current block” may mean “current transform block” or “transform target block”.
- filtering filtering target block.
- current block may mean “luma block of the current block” unless explicitly described as a chroma block.
- the “chroma block of the current block” may be expressed by including an explicit description of the chroma block, such as “chroma block” or “current chroma block”.
- “/” and “,” may be interpreted as “and/or”.
- “A/B” and “A, B” could be interpreted as “A and/or B”.
- “A/B/C” and “A, B, C” may mean “at least one of A, B and/or C”.
- the present disclosure relates to video/image coding for machines (VCM).
- VCM video/image coding for machines
- VCM refers to a compression technology for encoding/decoding a part of a source image/video or information obtained from a source image/video for the purpose of machine vision.
- an encoding/decoding target may be referred to as a feature.
- a feature may refer to information extracted from a source image/video based on a task purpose, requirements, surrounding environment, and the like.
- a feature may have an information type different from that of a source image/video, and accordingly, a compression method and expression format of a feature may also be different from that of a video source.
- VCM can be applied in a variety of applications.
- the VCM may be used to store or transmit object recognition information.
- the VCM is a vehicle location information collected from GPS, sensing information collected from LIDAR, radar, etc., and various vehicles It can be used to transmit control information to other vehicles or infrastructure.
- the VCM may be used to perform individual tasks of interconnected sensor nodes or devices.
- FIG. 1 is a diagram schematically illustrating a VCM system to which embodiments of the present disclosure may be applied.
- the VCM system may include an encoding device 10 and a decoding device 20 .
- the encoding apparatus 10 may generate a bitstream by compressing/encoding features/feature maps extracted from source images/videos, and transmit the generated bitstream to the decoding apparatus 20 through a storage medium or a network.
- the encoding device 10 may also be referred to as a feature encoding device.
- a feature/feature map can be created in each hidden layer of a neural network. The size and number of channels of the generated feature map may vary depending on the type of neural network or the location of the hidden layer.
- a feature map may be referred to as a feature set, and a feature or feature map may be referred to as 'feature information'.
- the encoding device 10 may include a feature obtaining unit 11 , an encoding unit 12 and a transmission unit 13 .
- the feature obtaining unit 11 may obtain a feature/feature map of a source image/video.
- the feature obtaining unit 11 may obtain a feature/feature map from an external device, for example, a feature extraction network.
- the feature obtaining unit 11 performs a feature receiving interface function.
- the feature obtaining unit 11 may acquire features/feature maps by executing a neural network (e.g., CNN, DNN, etc.) with the source image/video as an input. In this case, the feature acquisition unit 11 performs a feature extraction network function.
- a neural network e.g., CNN, DNN, etc.
- the encoding device 10 may further include a source image generator (not shown) for obtaining a source image/video.
- the source image generation unit may be implemented with an image sensor, a camera module, or the like, and may obtain the source image/video through a process of capturing, synthesizing, or generating the image/video.
- the generated source image/video may be transmitted to a feature extraction network and used as input data for extracting a feature/feature map.
- the encoder 12 may encode the feature/feature map acquired by the feature acquirer 11 .
- the encoder 12 may perform a series of procedures such as prediction, transformation, and quantization to increase encoding efficiency.
- Encoded data (encoded feature/feature map information) may be output in the form of a bitstream.
- a bitstream including coded feature/feature map information may be referred to as a VCM bitstream.
- the transmission unit 13 may obtain feature/feature map information or data output in the form of a bitstream, and may transmit it in the form of a file or streaming to the decoding device 20 or other external object through a digital storage medium or network.
- the digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, and SSD.
- the transmission unit 13 may include elements for generating a media file having a predetermined file format or elements for data transmission through a broadcasting/communication network.
- the transmission unit 13 may be provided as a transmission device separate from the encoding unit 12.
- the transmission device includes at least one processor for acquiring feature/feature map information or data output in the form of a bitstream and converting the data into a file.
- it may include a transmission unit that delivers in a streaming form.
- the decoding apparatus 20 may obtain feature/feature map information from the encoding apparatus 10 and restore the feature/feature map based on the obtained information.
- the decoding device 20 may include a receiving unit 21 and a decoding unit 22 .
- the receiver 21 may receive a bitstream from the encoding device 10, obtain feature/feature map information from the received bitstream, and transmit the obtained feature/feature map information to the decoder 22.
- the decoder 22 may decode the feature/feature map based on the obtained feature/feature map information.
- the decoder 22 may perform a series of procedures such as inverse quantization, inverse transform, and prediction corresponding to the operation of the encoder 14 to increase decoding efficiency.
- the decoding device 20 may further include a task analysis/rendering unit 23 .
- the task analysis/rendering unit 23 may perform task analysis based on the decoded feature/feature map. Also, the task analysis/rendering unit 23 may render the decoded feature/feature map in a form suitable for performing the task. Various machine (directed) tasks may be performed based on the task analysis result and the rendered feature/feature map.
- the VCM system can encode/decode features extracted from source images/videos according to user and/or machine requests, task objectives, and surrounding environments, and perform various machine (oriented) tasks based on the decoded features.
- the VCM system may be implemented by extending/redesigning a video/image coding system, and may perform various encoding/decoding methods defined in the VCM standard.
- FIG. 2 is a diagram schematically illustrating a VCM pipeline structure to which embodiments of the present disclosure may be applied.
- the VCM pipeline 200 may include a first pipeline 210 for image/video encoding/decoding and a second pipeline 220 for feature/feature map encoding/decoding.
- first pipeline 210 may be referred to as a video codec pipeline
- second pipeline 220 may be referred to as a feature codec pipeline.
- the first pipeline 210 may include a first stage 211 encoding an input image/video and a second stage 212 decoding the encoded image/video to generate a reconstructed image/video.
- the restored image/video may be used for human viewing, that is, for human vision.
- the second pipeline 220 includes a third stage 221 that extracts features/feature maps from input images/videos, a fourth stage 222 that encodes the extracted features/feature maps, and encoded features/feature maps.
- a fifth stage 223 of decoding the map to generate a reconstructed feature/feature map may be included.
- the reconstructed feature/feature map can be used for machine (vision) tasks.
- the machine (vision) task may mean a task in which an image/video is consumed by a machine.
- Machine (vision) tasks may be applied to service scenarios such as surveillance, intelligent transportation, smart city, intelligent industry, and intelligent content.
- the reconstructed feature/feature map may be used for human vision.
- the feature/feature map encoded in the fourth stage 222 may be transferred to the first stage 221 and used to encode an image/video.
- an additional bitstream may be generated based on the encoded feature/feature map, and the generated additional bitstream may be transferred to the second stage 222 and used to decode an image/video.
- the feature/feature map decoded in the fifth stage 223 may be transferred to the second stage 222 and used to decode the image/video.
- FIG. 2 shows a case in which the VCM pipeline 200 includes the first pipeline 210 and the second pipeline 220, this is illustrative only and the embodiments of the present disclosure are not limited thereto.
- the VCM pipeline 200 may include only the second pipeline 220, or the second pipeline 220 may be extended to a plurality of feature codec pipelines.
- the first stage 211 may be performed by an image/video encoder
- the second stage 212 may be performed by an image/video decoder.
- the third stage 221 is performed by a VCM encoder (or feature/feature map encoder)
- the fourth stage 222 is performed by a VCM decoder (or feature/feature map encoder). decoder).
- VCM encoder or feature/feature map encoder
- decoder or feature/feature map encoder
- FIG. 3 is a diagram schematically illustrating an image/video encoder to which embodiments of the present disclosure may be applied.
- the image/video encoder 300 includes an image partitioner 310, a predictor 320, a residual processor 330, and an entropy encoder 340. ), an adder 350, a filter 360, and a memory 370.
- the prediction unit 320 may include an inter prediction unit 321 and an intra prediction unit 322 .
- the residual processing unit 330 may include a transformer 332, a quantizer 333, a dequantizer 334, and an inverse transformer 335.
- the residual processing unit 330 may further include a subtractor 331 .
- the adder 350 may be referred to as a reconstructor or a reconstructed block generator.
- the above-described image segmentation unit 310, prediction unit 320, residual processing unit 330, entropy encoding unit 340, adder 350, and filtering unit 360 may be one or more hardware components (for example, an encoder chipset or processor).
- the memory 370 may include a decoded picture buffer (DPB) and may be configured by a digital storage medium.
- DPB decoded picture buffer
- the hardware components described above may further include the memory 370 as an internal/external component.
- the image divider 310 may divide an input image (or picture or frame) input to the image/video encoder 300 into one or more processing units.
- a processing unit may be referred to as a coding unit (CU).
- a coding unit may be partitioned recursively from a coding tree unit (CTU) or a largest coding unit (LCU) according to a quad-tree binary-tree ternary-tree (QTBTTT) structure.
- QTBTTT quad-tree binary-tree ternary-tree
- one coding unit may be divided into a plurality of coding units of deeper depth based on a quad tree structure, a binary tree structure, and/or a ternary structure.
- a quad tree structure may be applied first and a binary tree structure and/or ternary structure may be applied later.
- a binary tree structure may be applied first.
- An image/video coding procedure according to the present disclosure may be performed based on a final coding unit that is not further divided.
- the maximum coding unit may be directly used as the final coding unit based on the coding efficiency according to the video characteristics, or the coding unit may be recursively divided into coding units of lower depth as needed to obtain an optimal coding unit.
- a coding unit having a size of may be used as the final coding unit.
- the coding procedure may include procedures such as prediction, transformation, and restoration to be described later.
- the processing unit may further include a prediction unit (PU) or a transform unit (TU).
- PU prediction unit
- TU transform unit
- each of the prediction unit and the transform unit may be divided or partitioned from the above-described final coding unit.
- the prediction unit may be a unit of sample prediction
- the transform unit may be a unit for deriving transform coefficients and/or a unit for deriving a residual signal from transform coefficients.
- an MxN block may represent a set of samples or transform coefficients consisting of M columns and N rows.
- a sample may generally represent a pixel or a pixel value, may represent only a pixel/pixel value of a luma component, or only a pixel/pixel value of a chroma component.
- a sample may be used as a term corresponding to a pixel or a pel.
- the video/video encoder 300 subtracts the prediction signal (predicted block, prediction sample array) output from the inter prediction unit 321 or the intra prediction unit 322 from the input video signal (original block, original sample array).
- a residual signal residual block, residual sample array
- a unit for subtracting a prediction signal (prediction block, prediction sample array) from an input video signal (original block, original sample array) in the video/video encoder 300 is referred to as a subtraction unit 331. It can be.
- the prediction unit may perform prediction on a block to be processed (hereinafter referred to as a current block) and generate a predicted block including predicted samples of the current block.
- the prediction unit may determine whether intra prediction or inter prediction is applied in units of current blocks or CUs.
- the prediction unit may generate various types of information related to prediction, such as prediction mode information, and transmit them to the entropy encoding unit 340 .
- Prediction-related information may be encoded in the entropy encoding unit 340 and output in the form of a bitstream.
- the intra predictor 322 may predict a current block by referring to samples in the current picture.
- the referenced samples may be located in the neighborhood of the current block or may be located apart from each other according to the prediction mode.
- prediction modes may include a plurality of non-directional modes and a plurality of directional modes.
- the non-directional mode may include, for example, a DC mode and a planar mode.
- the directional modes may include, for example, 33 directional prediction modes or 65 directional prediction modes according to the degree of detail of the prediction direction. However, this is just an example, and more or less directional prediction modes may be used according to settings.
- the intra prediction unit 322 may determine a prediction mode applied to the current block by using a prediction mode applied to neighboring blocks.
- the inter-prediction unit 321 may derive a predicted block for a current block based on a reference block (reference sample array) specified by a motion vector on a reference picture.
- motion information may be predicted in units of blocks, subblocks, or samples based on correlation of motion information between neighboring blocks and the current block.
- Motion information may include a motion vector and a reference picture index.
- the motion information may further include inter prediction direction (L0 prediction, L1 prediction, Bi prediction, etc.) information.
- a neighboring block may include a spatial neighboring block present in the current picture and a temporal neighboring block present in the reference picture.
- a reference picture including a reference block and a reference picture including a temporal neighboring block may be the same or different.
- a temporal neighboring block may be referred to as a collocated reference block, a collocated CU (colCU), and the like, and a reference picture including a temporal neighboring block may be referred to as a collocated picture (colPic) .
- the inter prediction unit 321 constructs a motion information candidate list based on neighboring blocks, and generates information indicating which candidate is used to derive a motion vector and/or reference picture index of a current block. can do. Inter prediction may be performed based on various prediction modes.
- the inter prediction unit 321 may use motion information of neighboring blocks as motion information of the current block.
- the residual signal may not be transmitted unlike the merge mode.
- MVP motion vector prediction
- the prediction unit 320 may generate prediction signals based on various prediction methods. For example, the prediction unit may apply intra-prediction or inter-prediction to predict one block, or simultaneously apply intra-prediction and inter-prediction. This can be called combined inter and intra prediction (CIIP). Also, the prediction unit may be based on an intra block copy (IBC) prediction mode or a palette mode for block prediction.
- IBC intra block copy
- the IBC prediction mode or the palette mode can be used for video/video coding of content such as games, for example, such as screen content coding (SCC). IBC basically performs prediction within the current picture, but may be performed similarly to inter prediction in that a reference block is derived within the current picture. That is, IBC may use at least one of the inter prediction techniques described in this disclosure.
- Palette mode can be viewed as an example of intra coding or intra prediction. When the palette mode is applied, a sample value within a picture may be signaled based on information about a palette table and a palette index.
- the prediction signal generated by the prediction unit 320 may be used to generate a reconstruction signal or a residual signal.
- the transform unit 332 may generate transform coefficients by applying a transform technique to the residual signal.
- the transform technique uses at least one of a Discrete Cosine Transform (DCT), a Discrete Sine Transform (DST), a Karhunen-Loeve Transform (KLT), a Graph-Based Transform (GBT), or a Conditionally Non-linear Transform (CNT).
- DCT Discrete Cosine Transform
- DST Discrete Sine Transform
- KLT Karhunen-Loeve Transform
- GBT Graph-Based Transform
- CNT Conditionally Non-linear Transform
- GBT means a conversion obtained from the graph when relation information between pixels is expressed as a graph.
- CNT means a transformation obtained based on generating a prediction signal using all previously reconstructed pixels.
- the conversion process may be applied to square pixel blocks having the
- the quantization unit 333 quantizes the transform coefficients and transmits them to the entropy encoding unit 340, and the entropy encoding unit 340 may encode the quantized signal (information on the quantized transform coefficients) and output it as a bitstream. There is. Information about quantized transform coefficients may be referred to as residual information.
- the quantization unit 333 may rearrange the block-type quantized transform coefficients into a 1-dimensional vector form based on the coefficient scan order, and the quantized transform coefficients based on the quantized transform coefficients in the 1-dimensional vector form. You can also generate information about them.
- the entropy encoding unit 340 may perform various encoding methods such as, for example, exponential Golomb, context-adaptive variable length coding (CAVLC), and context-adaptive binary arithmetic coding (CABAC).
- the entropy encoding unit 340 may encode together or separately information necessary for image/video reconstruction (e.g., values of syntax elements, etc.) in addition to quantized transform coefficients.
- Encoded information e.g., encoded image/video information
- NAL network abstraction layer
- the image/video information may further include information about various parameter sets such as an adaptation parameter set (APS), a picture parameter set (PPS), a sequence parameter set (SPS), or a video parameter set (VPS). Also, the image/video information may further include general constraint information. In addition, the image/video information may further include a method of generating and using the encoded information, a purpose, and the like. In the present disclosure, information and/or syntax elements transmitted/signaled from a video/video encoder to a video/video decoder may be included in the video/video information. Image/video information may be encoded through the above-described encoding procedure and included in a bitstream. The bitstream may be transmitted over a network or stored in a digital storage medium.
- APS adaptation parameter set
- PPS picture parameter set
- SPS sequence parameter set
- VPS video parameter set
- VPS video parameter set
- the image/video information may further include general constraint information.
- the image/video information may further include a method of generating and using the
- the network may include a broadcasting network and/or a communication network
- the digital storage medium may include various storage media such as USB, SD, CD, DVD, Blu-ray, HDD, and SSD.
- a transmission unit (not shown) that transmits the signal output from the entropy encoding unit 340 and/or a storage unit (not shown) that stores the signal may be configured as internal/external elements of the video/video encoder 300, or The transmission unit may be included in the entropy encoding unit 340 .
- Quantized transform coefficients output from the quantization unit 333 may be used to generate a prediction signal.
- a residual signal residual block or residual samples
- the adder 350 adds the reconstructed residual signal to the prediction signal output from the inter prediction unit 321 or the intra prediction unit 322 to obtain a reconstructed signal (a reconstructed picture, a reconstructed block, and a reconstructed sample array). can be created
- a predicted block may be used as a reconstruction block.
- the adder 350 may be called a restoration unit or a restoration block generation unit.
- the generated reconstruction signal may be used for intra prediction of the next processing target block in the current picture, or may be used for inter prediction of the next picture after filtering as described later.
- LMCS luma mapping with chroma scaling
- the filtering unit 360 may improve subjective/objective picture quality by applying filtering to the reconstructed signal.
- the filtering unit 360 may generate a modified reconstructed picture by applying various filtering methods to the reconstructed picture, and store the modified reconstructed picture in the memory 370, specifically the DPB of the memory 370. can be stored in Various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, and the like.
- the filtering unit 360 may generate various types of filtering-related information and transmit them to the entropy encoding unit 340 . Filtering-related information may be encoded in the entropy encoding unit 340 and output in the form of a bitstream.
- the modified reconstructed picture transmitted to the memory 370 may be used as a reference picture in the inter prediction unit 321 . Through this, prediction mismatch in the encoder and decoder stages can be avoided, and encoding efficiency can be improved.
- the DPB of the memory 370 may store the modified reconstructed picture to be used as a reference picture in the inter prediction unit 321 .
- the memory 370 may store motion information of a block in the current picture from which motion information is derived (or encoded) and/or motion information of blocks in a previously reconstructed picture.
- the stored motion information may be transmitted to the inter prediction unit 321 to be used as motion information of a spatial neighboring block or motion information of a temporal neighboring block.
- the memory 370 may store reconstructed samples of reconstructed blocks in the current picture and transfer the stored reconstructed samples to the intra predictor 322 .
- the video/video encoder basically described with reference to FIG. 3 in that a VCM encoder (or feature/feature map encoder) performs a series of procedures such as prediction, transformation, and quantization to encode a feature/feature map. It may have the same/similar structure to (300). However, the VCM encoder differs from the video/video encoder 300 in that it encodes features/feature maps, and accordingly, the names of each unit (or component) (e.g., video segmentation unit 310, etc.) ) and its specific operation content may differ from that of the video/video encoder 300. Detailed operation of the VCM encoder will be described later.
- FIG. 4 is a diagram schematically illustrating an image/video decoder to which embodiments of the present disclosure may be applied.
- the video/video decoder 400 includes an entropy decoder 410, a residual processor 420, a predictor 430, an adder 440, A filter 450 and a memory 460 may be included.
- the predictor 430 may include an inter predictor 431 and an intra predictor 432 .
- the residual processing unit 420 may include a dequantizer 421 and an inverse transformer 422 .
- the above-described entropy decoding unit 410, residual processing unit 420, prediction unit 430, adder 440, and filtering unit 450 may be one hardware component (eg, decoder chipset or processor) according to an embodiment. can be configured by Also, the memory 460 may include a decoded picture buffer (DPB) and may be configured by a digital storage medium.
- the hardware component may further include the memory 460 as an internal/external component.
- the image/video decoder 400 may restore the image/video in accordance with the process in which the image/video information is processed in the image/video encoder 300 of FIG. 3 .
- the image/video decoder 400 may derive units/blocks based on block division related information obtained from a bitstream.
- the video/video decoder 400 may perform decoding using a processing unit applied in the video/video encoder.
- a processing unit of decoding may be, for example, a coding unit, and a coding unit may be partitioned from a coding tree unit or a largest coding unit according to a quad tree structure, a binary tree structure, and/or a ternary tree structure.
- One or more transform units may be derived from a coding unit.
- the restored video signal decoded and outputted through the video/video decoder 400 may be reproduced through a playback device.
- the video/video decoder 400 may receive a signal output from the encoder of FIG. 3 in the form of a bitstream, and the received signal may be decoded through the entropy decoding unit 410 .
- the entropy decoding unit 410 may parse the bitstream to derive information (e.g., image/video information) necessary for image restoration (or picture restoration).
- the image/video information may further include information about various parameter sets such as an adaptation parameter set (APS), a picture parameter set (PPS), a sequence parameter set (SPS), or a video parameter set (VPS).
- the image/video information may further include general constraint information.
- the image/video information may include a method of generating and using the decoded information, a purpose, and the like.
- the image/video decoder 400 may decode a picture further based on parameter set information and/or general restriction information. Signaled/received information and/or syntax elements may be obtained from a bitstream by being decoded through a decoding procedure.
- the entropy decoding unit 410 decodes information in a bitstream based on a coding method such as exponential Golomb coding, CAVLC, or CABAC, and quantizes values of syntax elements required for image reconstruction and transform coefficients for residuals. values can be output.
- the CABAC entropy decoding method receives bins corresponding to each syntax element in a bitstream, and receives decoding target syntax element information and decoding information of neighboring and decoding target blocks or symbols/bins decoded in the previous step. It is possible to determine a context model using the information of , predict a bin occurrence probability according to the determined context model, and perform arithmetic decoding of the bin to generate a symbol corresponding to the value of each syntax element. there is. At this time, the CABAC entropy decoding method may update the context model by using information on the decoded symbol/bin for the context model of the next symbol/bin after determining the context model.
- prediction-related information is provided to the prediction unit (inter prediction unit 432 and intra prediction unit 431), and entropy decoding is performed by the entropy decoding unit 410.
- Dual values that is, quantized transform coefficients and related parameter information may be input to the residual processing unit 420 .
- the residual processor 420 may derive a residual signal (residual block, residual samples, residual sample array).
- information about filtering may be provided to the filtering unit 450 .
- a receiver for receiving a signal output from the video/video encoder may be further configured as an internal/external element of the video/video decoder 400, or the receiver may be a component of the entropy decoding unit 410. It could be.
- the video/video decoder according to the present disclosure may be referred to as a video/video decoding device, and the video/video decoder may be divided into an information decoder (video/video information decoder) and a sample decoder (video/video sample decoder). .
- the information decoder may include the entropy decoding unit 410, and the sample decoder may include an inverse quantization unit 321, an inverse transform unit 322, an adder 440, a filtering unit 450, and a memory 460. , may include at least one of an inter predictor 432 and an intra predictor 431.
- the inverse quantization unit 421 may inversely quantize the quantized transform coefficients and output the transform coefficients.
- the inverse quantization unit 421 may rearrange the quantized transform coefficients in the form of a 2D block. In this case, rearrangement may be performed based on a coefficient scanning order performed by the video/video encoder.
- the inverse quantization unit 321 may perform inverse quantization on the quantized transform coefficients using a quantization parameter (e.g., quantization step size information) and obtain transform coefficients.
- a quantization parameter e.g., quantization step size information
- a residual signal (residual block, residual sample array) is obtained by inverse transforming the transform coefficients.
- the prediction unit 430 may perform prediction on the current block and generate a predicted block including prediction samples of the current block.
- the predictor may determine whether intra-prediction or inter-prediction is applied to the current block based on the prediction information output from the entropy decoder 410, and may determine a specific intra/inter prediction mode.
- the prediction unit 420 may generate prediction signals based on various prediction methods.
- the predictor may apply intra-prediction or inter-prediction to predict one block, as well as apply intra-prediction and inter-prediction at the same time. This can be called combined inter and intra prediction (CIIP).
- the prediction unit may be based on an intra block copy (IBC) prediction mode or a palette mode for block prediction.
- IBC intra block copy
- the IBC prediction mode or the palette mode can be used for video/video coding of content such as games, for example, such as screen content coding (SCC).
- SCC screen content coding
- IBC basically performs prediction within the current picture, but may be performed similarly to inter prediction in that a reference block is derived within the current picture. That is, IBC may use at least one of the inter prediction techniques described in this document.
- Palette mode can be viewed as an example of intra coding or intra prediction. When the palette mode is applied, information on a palette table and a palette index may be included in image/video information and signal
- the intra predictor 431 may predict a current block by referring to samples in the current picture. Referenced samples may be located in the neighborhood of the current block or may be located apart from each other according to the prediction mode.
- prediction modes may include a plurality of non-directional modes and a plurality of directional modes.
- the intra predictor 431 may determine a prediction mode applied to the current block by using a prediction mode applied to neighboring blocks.
- the inter-prediction unit 432 may derive a predicted block for a current block based on a reference block (reference sample array) specified by a motion vector on a reference picture.
- motion information may be predicted in units of blocks, subblocks, or samples based on correlation of motion information between neighboring blocks and the current block.
- Motion information may include a motion vector and a reference picture index.
- the motion information may further include inter prediction direction (L0 prediction, L1 prediction, Bi prediction, etc.) information.
- a neighboring block may include a spatial neighboring block present in the current picture and a temporal neighboring block present in the reference picture.
- the inter predictor 432 may construct a motion information candidate list based on neighboring blocks and derive a motion vector and/or reference picture index of the current block based on the received candidate selection information. Inter prediction may be performed based on various prediction modes, and prediction information may include information indicating an inter prediction mode for a current block.
- the adder 440 restores the obtained residual signal by adding it to the prediction signal (predicted block, prediction sample array) output from the prediction unit (including the inter prediction unit 432 and/or the intra prediction unit 431). Signals (reconstructed picture, reconstructed block, reconstructed sample array) can be generated. When there is no residual for the block to be processed, such as when the skip mode is applied, a predicted block may be used as a reconstruction block.
- the adder 440 may be called a restoration unit or a restoration block generation unit.
- the generated reconstruction signal may be used for intra prediction of the next processing target block in the current picture, output after filtering as described later, or may be used for inter prediction of the next picture.
- LMCS luma mapping with chroma scaling
- the filtering unit 450 may improve subjective/objective picture quality by applying filtering to the reconstructed signal.
- the filtering unit 450 may generate a modified reconstructed picture by applying various filtering methods to the reconstructed picture, and store the modified reconstructed picture in the memory 460, specifically the DPB of the memory 460.
- Various filtering methods may include, for example, deblocking filtering, sample adaptive offset, adaptive loop filter, bilateral filter, and the like.
- a (modified) reconstructed picture stored in the DPB of the memory 460 may be used as a reference picture in the inter prediction unit 432 .
- the memory 460 may store motion information of a block in the current picture from which motion information is derived (or decoded) and/or motion information of blocks in a previously reconstructed picture.
- the stored motion information may be transmitted to the inter prediction unit 432 to be used as motion information of spatial neighboring blocks or motion information of temporal neighboring blocks.
- the memory 460 may store reconstructed samples of reconstructed blocks in the current picture and transfer them to the intra prediction unit 431 .
- the VCM decoder (or feature/feature map decoder) basically performs a series of procedures such as prediction, inverse transformation, and inverse quantization to decode the feature/feature map. It may have the same/similar structure as the video decoder 400. However, the VCM decoder differs from the video/video decoder 400 in that it targets features/feature maps for decoding, and accordingly, the names of each unit (or component) (e.g., DPB, etc.) and its specific operation. It may be different from the image/video decoder 400 in content. The operation of the VCM decoder may correspond to the operation of the VCM encoder, and its detailed operation will be described later in detail.
- FIG. 5 is a flowchart schematically illustrating a feature/feature map encoding procedure to which embodiments of the present disclosure may be applied.
- a feature/feature map encoding procedure may include a prediction procedure (S510), a residual processing procedure (S520), and an information encoding procedure (S530).
- the prediction procedure ( S510 ) may be performed by the prediction unit 320 described above with reference to FIG. 3 .
- the intra prediction unit 322 may predict a current block (ie, a set of feature elements to be currently encoded) by referring to feature elements in a current feature/feature map. Intra prediction may be performed based on spatial similarity of feature elements constituting a feature/feature map. For example, feature elements included in the same region of interest (RoI) within an image/video may be estimated to have similar data distribution characteristics. Accordingly, the intra predictor 322 may predict the current block by referring to the feature elements of the region of interest including the current block and with the undulations restored. In this case, the referenced feature elements may be located adjacent to the current block or may be located apart from the current block according to the prediction mode.
- a current block ie, a set of feature elements to be currently encoded
- Intra prediction may be performed based on spatial similarity of feature elements constituting a feature/feature map. For example, feature elements included in the same region of interest (RoI) within an image/video may be estimated to have similar data distribution characteristics. Accordingly, the intra predict
- Intra prediction modes for feature/feature map encoding may include a plurality of non-directional prediction modes and a plurality of directional prediction modes.
- Non-directional prediction modes may include, for example, prediction modes corresponding to a DC mode and a planner mode of an image/video encoding procedure.
- the directional modes may include, for example, prediction modes corresponding to 33 directional modes or 65 directional modes of an image/video encoding procedure.
- this is just an example, and the type and number of intra prediction modes may be set/changed in various ways according to embodiments.
- the inter predictor 321 may predict a current block based on a reference block specified by motion information on a reference feature/feature map (ie, a set of referenced feature elements). Inter prediction may be performed based on temporal similarity of feature elements constituting a feature/feature map. For example, temporally contiguous features may have similar data distribution characteristics. Accordingly, the inter predictor 321 may predict the current block by referring to the restored feature elements of features temporally adjacent to the current feature.
- the motion information for specifying referenced feature elements may include a motion vector and a reference feature/feature map index.
- the motion information may further include information about an inter prediction direction (e.g., L0 prediction, L1 prediction, Bi prediction, etc.).
- a neighboring block may include a spatial neighboring block present in a current feature/feature map and a temporal neighboring block present in a reference feature/feature map.
- the reference feature/feature map including the reference block and the reference feature/feature map including the temporal neighboring block may be the same or different.
- a temporal neighboring block may be referred to as a collocated reference block, etc.
- a reference feature/feature map including a temporal neighboring block may be referred to as a collocated feature/feature map.
- the inter prediction unit 321 constructs a motion information candidate list based on neighboring blocks and generates information indicating which candidate is used to derive a motion vector and/or a reference feature/feature map index of the current block.
- Inter prediction may be performed based on various prediction modes.
- the inter prediction unit 321 may use motion information of neighboring blocks as motion information of the current block.
- the residual signal may not be transmitted unlike the merge mode.
- MVP motion vector prediction
- motion vectors of neighboring blocks are used as motion vector predictors and motion vector differences are signaled to determine the motion vectors of the current block.
- the prediction unit 320 may generate a prediction signal based on various prediction methods other than intra prediction and inter prediction described above.
- the prediction signal generated by the prediction unit 320 may be used to generate a residual signal (residual block, residual feature elements) (S520).
- the residual processing procedure ( S520 ) may be performed by the residual processing unit 330 described above with reference to FIG. 3 .
- (quantized) transform coefficients may be generated through a transform and/or quantization procedure for the residual signal, and the entropy encoding unit 340 converts information about the (quantized) transform coefficients into bits as residual information. It can be encoded in the stream (S530).
- the entropy encoding unit 340 may encode information necessary for feature/feature map reconstruction, for example, prediction information (e.g., prediction mode information, motion information, etc.) into the bitstream.
- the feature/feature map encoding procedure encodes information for feature/feature map reconstruction (e.g., prediction information, residual information, partitioning information, etc.) and outputs it in a bitstream form (S530), as well as A procedure for generating a reconstructed feature/feature map for the feature map and a procedure for applying in-loop filtering to the reconstructed feature/feature map (optional) may be further included.
- information for feature/feature map reconstruction e.g., prediction information, residual information, partitioning information, etc.
- S530 bitstream form
- a procedure for generating a reconstructed feature/feature map for the feature map and a procedure for applying in-loop filtering to the reconstructed feature/feature map (optional) may be further included.
- the VCM encoder may derive the (modified) residual feature(s) from the quantized transform coefficient(s) through inverse quantization and inverse transformation, and the predicted feature(s) and the (modified) residual
- a restoration feature/feature map can be created based on the feature(s).
- the reconstructed feature/feature map generated in this way may be the same as the reconstructed feature/feature map generated by the VCM decoder.
- a modified reconstructed feature/feature map may be generated through the in-loop filtering procedure on the reconstructed feature/feature map.
- the modified reconstructed feature/feature map is stored in a decoded feature buffer (DFB) or memory, and can be used as a reference feature/feature map in a subsequent feature/feature map prediction procedure.
- (in-loop) filtering-related information may be encoded and output in the form of a bitstream.
- noise that may occur during feature/feature map coding may be removed, and performance of a feature/feature map-based task performance may be improved.
- by performing an in-loop filtering procedure at both the encoder end and the decoder end it is possible to ensure uniformity of prediction results, improve the reliability of feature/feature map coding, and reduce the amount of data transmission for feature/feature map coding. there is.
- FIG. 6 is a flowchart schematically illustrating a feature/feature map decoding procedure to which embodiments of the present disclosure may be applied.
- the feature/feature map decoding procedure includes image/video information acquisition procedure (S610), feature/feature map restoration procedure (S620 to S640), and in-loop filtering procedure for the reconstructed feature/feature map (S650).
- S610 image/video information acquisition procedure
- S620 to S640 feature/feature map restoration procedure
- S650 in-loop filtering procedure for the reconstructed feature/feature map
- the feature/feature map reconstruction procedure is applied to the prediction signal and the residual signal obtained through the process of inter/intra prediction (S620) and residual processing (S630), inverse quantization of quantized transform coefficients, and inverse transformation) described in the present disclosure. can be performed based on A modified reconstructed feature/feature map may be generated through an in-loop filtering procedure on the reconstructed feature/feature map, and the modified reconstructed feature/feature map may be output as a decoded feature/feature map.
- the decoded feature/feature map may be stored in a decoded feature buffer (DFB) or memory and used as a reference feature/feature map in an inter-prediction procedure when decoding a feature/feature map thereafter.
- the above-described in-loop filtering procedure may be omitted.
- the reconstructed feature/feature map may be output as it is as a decoded feature/feature map, stored in the decoded feature buffer (DFB) or memory, and then referenced in the inter prediction procedure when decoding the feature/feature map/feature map. can be used as
- Embodiments of the present disclosure propose a filtering process and a method of generating a related bitstream for compensating for a decrease in information amount due to compression of an activation (feature) map generated in a hidden layer of a deep neural network.
- the input data input to the deep neural network goes through the association process of several hidden layers, and the operation result of each hidden layer is a feature/channel number with various sizes and channels depending on the type of deep neural network being used and the position of the hidden layer in the deep neural network. output as a feature map.
- FIG. 7 is a diagram illustrating an example of a feature extraction and restoration method to which embodiments of the present disclosure may be applied.
- the feature extraction network 710 may extract an activation (feature) map of an intermediate layer of a deep neural network from a source image/video and output the extracted feature map.
- Feature extraction network 710 may be a set of hidden layers that are continued from the input of the deep neural network.
- the encoding device 720 may compress the output feature map and output it in the form of a bitstream, and the decoding device 730 may restore the (compressed) feature map from the output bitstream.
- the encoding device 720 may correspond to the encoder 12 of FIG. 1
- the decoding device 720 may correspond to the decoder 22 of FIG. 1 .
- the task network 740 may perform a task based on the restored feature map.
- FIG. 8 is a diagram illustrating an example of a feature extraction method using a feature extraction network 710. Referring to FIG.
- the feature extraction network 710 may output a feature set of the video source by performing a feature extraction operation by receiving a video source (Image/Video).
- a feature set may include a plurality of features (C 0 , C 1 , ⁇ , C n ) extracted from a video source and may be expressed as a feature map.
- Each feature (C 0 , C 1 , ⁇ , C n ) includes a plurality of feature elements and may have different data distribution characteristics.
- W, H, and C may respectively mean the width, height, and number of channels of a video source.
- the number of channels (C) of the video source may be determined based on the video format of the video source. For example, when a video source has an RGB image format, the number of channels (C) of the video source may be three.
- W', H', and C' may mean the width, height, and number of channels of the feature set, respectively.
- the number of channels (C′) of a feature set may be equal to the total number (n+1) of features (C 0 , C 1 , ... , C n ) extracted from a video source. In one example, the number of channels (C′) of the feature set may be greater than the number of channels (C) of the video source.
- the attributes (W', H', C') of the feature set may vary depending on the attributes (W, H, C) of the video source. For example, as the number of channels (C) of a video source increases, the number of channels (C′) of a feature set may also increase.
- the attributes (W', H', and C') of the feature set may vary depending on the type and attribute of the feature extraction network 710. For example, when the feature extraction network 710 is implemented as an artificial neural network (eg, CNN, DNN, etc.), each feature (C 0 , C 1 , ... , C n ) is located at the position of the output layer. Accordingly, the attributes (W', H', C') of the feature set may also vary.
- Video sources and feature sets may have different data distribution characteristics.
- a video source may typically consist of one (Grayscale image) channel or three (RGB image) channels. Pixels included in the video source may have the same range of integer values for all channels and may have non-negative values. Also, each pixel value may be evenly distributed within a predetermined integer value range.
- the feature set may consist of channels of various numbers (e.g., 32, 64, 128, 256, 512, etc.) according to the type of feature extraction network 710 (e.g., CNN, DNN, etc.) and layer location. there is. Feature elements included in the feature set may have different ranges of real values for each channel and may have negative values. In addition, each feature element value may be intensively distributed in a specific region within a predetermined real value range.
- FIG. 9 is a diagram showing an example of extracted features
- FIG. 10 is a diagram showing an example of the size of an extracted feature set.
- FIG. 9 The left side of FIG. 9 shows a video source (Image/Video), and the right side of FIG. 9 shows a feature map having 64 features.
- 64 features channels
- the size of the width and height of each feature is also different from the width and height of the video source.
- the size of a single feature is smaller than the size of the video source, but since the number of channels in a feature is greater than the number of channels in the video source, the sum of the sizes of all features can be larger than the size of the video source.
- FIG. 10(a) shows the size of a video source (Image/Video), and FIG. 10(b) shows a feature map having 256 channels.
- FIG. 10 although the size of individual features is smaller than that of the video source, the total size (size of the feature map) is greater than that of the video source due to the increase in the number of channels.
- Feature map conversion (or feature dimension conversion) can be used as a method of reducing the size of a feature map, and an example of a method of reducing the size of a feature map through feature dimension conversion is shown in FIG. 11 .
- the feature conversion unit 1110 converts the extracted feature map output from the feature extraction network 710 into a low-dimensional feature map, and the encoding device 720 can encode a low-dimensional feature map and output it in the form of a bitstream.
- the decoding device 730 decodes the low-dimensional feature map from the bitstream, and the inverse feature transform unit 1120 inverse transforms the low-dimensional feature map to obtain a high-dimensional feature map. can be converted to
- the function of the inverse feature transform unit 1120 may be to reconstruct a low-dimensional feature map into a high-dimensional feature map and output a reconstructed feature map.
- the dimension of the reconstructed feature map may be the same as the dimension before being input to the feature extraction network 710 .
- the present disclosure proposes embodiments of minimizing a difference (or error) between a feature map before application of a feature dimension transformation technique and a reconstructed feature map.
- Embodiment 1 is an embodiment of a filtering method for compensating for information lost in the process of reducing the dimensionality of a feature map.
- 12 is a flowchart illustrating a feature encoding method according to an exemplary embodiment
- FIG. 14 is a flowchart illustrating a feature decoding method according to an exemplary embodiment.
- the feature encoding apparatus 10 may extract a feature map from an image and transform the extracted feature map into a low-dimensional image (S1210). That is, the feature encoding apparatus 10 may derive a transformed feature map based on the extracted feature map.
- the feature encoding apparatus 10 may encode and decode the transformed feature map again (S1220), and inversely transform the decoded feature map (S1230) to derive the inversely transformed feature map. That is, the feature encoding apparatus 10 may derive an inversely transformed feature map based on the transformed feature map.
- the feature encoding apparatus 10 may derive filtering information based on the inversely transformed feature map (S1240) and encode the transformed feature map and the derived filtering information (S1250).
- the filtering information may include information indicating whether filtering is applied or not and filter parameters used to perform filtering.
- filters may be used as filters applied to the filtering.
- SAO sample adaptive offset
- ALF adaptive loop filter
- CCALF cross component ALF
- an in-loop filter is used to compensate for a difference between an original picture and a reconstructed picture generated during encoding/decoding.
- ALF compares the original picture and the reconstructed picture to determine information such as whether to apply ALF, ALF shape, and ALF parameters, and then signals and applies the information to the reconstructed picture, so that the reconstructed picture has values close to the original picture. It is a technology that compensates in pixel units so that This is because ALF is based on a Wiener Filter that makes the original picture and the restored picture similar.
- FIG. 13 An example of the type of ALF filter that can be used for error compensation is shown in FIG. 13 .
- 13(a) shows a 5x5 diamond-shaped ALF filter
- FIG. 13(b) shows a 7x7 diamond-shaped ALF filter.
- information such as whether ALF is to be applied, whether or not to apply the decision unit, filter shape, and filter parameter may be determined regardless of VVC.
- the ALF filter type exemplified in FIG. 13 is applied to a luminance component/chrominance component, and in the present disclosure, in consideration of the fact that a feature map is composed of a plurality of channels, a filter type different from that of FIG. 13 Filters can be used.
- the shape of the filter applied to each feature may be different according to the characteristics of the feature, and the same type of filter may be applied to all features. Since the filter parameter is information for minimizing errors, it may be generated differently for each application unit of the filter.
- CCALF is a method of applying ALF by utilizing a correlation between a luminance component and a color difference component. Therefore, when applying CCALF as a feature map target, a CCALF parameter can be generated using correlation between feature channels and applied to filtering.
- the feature decoding apparatus 20 may obtain a (low-dimensionally converted) feature map and filtering information from a bitstream (S1410).
- the feature decoding apparatus 20 may inversely transform the feature map into a higher dimension (S1420), and filter the feature map inversely transformed into a higher dimension based on the filtering information (S1430), thereby compensating for an error due to the dimensional transformation. .
- An existing encoding/decoding process may be a filtering process performed by the encoding device 720 and the decoding device 730 of FIG. 11 .
- the present disclosure proposes a method of integrating two filtering processes into one. That is, filtering (second filtering) may be applied only to a feature map inversely transformed to a higher dimension (dimensionality restored) without performing the first filtering.
- filter parameters required for the first filtering process and filter parameters required for the second filtering process may be integrated into one.
- Embodiment 2 is an embodiment of a method for deriving necessary information for applying the second filtering. Embodiment 2 may be classified into the following embodiments according to a feature map used to derive filtering information.
- Embodiment 2-1 is a method of generating filtering information based on the feature map extracted from the feature extraction network 1110 and the low-dimensionally transformed feature map.
- FIG. 15 is a flowchart illustrating feature encoding methods according to Example 2-1
- FIG. 17 is a flowchart illustrating a feature decoding method according to Example 2-1.
- the feature encoding apparatus 10 may extract a feature map from an image and transform the extracted feature map into a low-dimensional image (S1510). That is, the feature encoding apparatus 10 may derive a transformed feature map based on the extracted feature map.
- the feature encoding apparatus 10 may inverse transform the transformed feature map into a higher dimension (same dimension as the extracted feature map) (S1520), and derive filtering information based on the extracted feature map and the inverse transformed feature map. (S1530).
- the feature decoding apparatus 20 may obtain a (low-dimensionally converted) feature map and filtering information from a bitstream (S1710).
- the feature decoding apparatus 20 may inversely transform the feature map into a higher dimension (S1720), and filter the feature map inversely transformed into a higher dimension based on the filtering information (S1730), thereby compensating for an error due to the dimensional transformation. .
- Example 2-1 since filtering information can be derived only through feature map transformation and inverse transformation, the complexity of the process of deriving filtering information can be reduced.
- Embodiment 2-2 is a method of generating filtering information based on a feature map extracted from the feature extraction network 1110 and a feature map to which low-dimensional transformation, encoding, decoding, and inverse transformation are applied.
- FIG. 16 is a flowchart illustrating feature encoding methods according to Example 2-2
- FIG. 17 is a flowchart illustrating a feature decoding method according to Example 2-2.
- the feature encoding apparatus 10 may extract a feature map from an image and transform the extracted feature map into a low-dimensional image (S1610). That is, the feature encoding apparatus 10 may derive a transformed feature map based on the extracted feature map.
- the feature encoding apparatus 10 may encode the converted feature map and decode the encoded feature map again (S1620).
- the feature encoding apparatus 10 may inversely transform the decoded feature map into a higher dimension (same dimension as the extracted feature map) (S1630), and derive filtering information based on the extracted feature map and the inversely transformed feature map. It can (S1640).
- the inverse transformed feature map corresponds to a feature map that has undergone feature transformation, encoding, decoding, and inverse transformation processes.
- the transformed feature map and filtering information may be encoded and signaled to the feature decoding apparatus 20 .
- the feature decoding apparatus 20 may obtain a (low-dimensionally converted) feature map and filtering information from a bitstream (S1710).
- the feature decoding apparatus 20 may inversely transform the feature map into a higher dimension (S1720), and filter the feature map inversely transformed into a higher dimension based on the filtering information (S1730), thereby compensating for an error due to the dimensional transformation. .
- the feature map extracted through the feature extraction network 1110 has float range data for each pixel, it may be a heavy burden in terms of implementation and calculation complexity. To solve this problem, a quantization process needs to be performed so that the feature map exists within a specific bit-depth range.
- Embodiment 2-3 is a method of generating filtering information based on a feature map to which quantization is applied and a feature map to which quantization, transformation, and inverse transformation are applied.
- 18 is a flowchart illustrating a feature encoding method according to the embodiment 2-3
- FIG. 19 is a flowchart illustrating a feature decoding method according to the embodiment 2-3.
- the feature encoding apparatus 10 may extract a feature map from an image and quantize the extracted feature map (S1810). Also, the feature encoding apparatus 10 may transform the quantized feature map into a low-dimensional one (S1820) and inversely transform the transformed feature map (S1830).
- the feature encoding apparatus 10 may derive filtering information based on the quantized feature map and the inverse transformed feature map (S1840).
- the inversely transformed feature map may be a feature map that has undergone quantization, transformation, and inverse transformation.
- the feature decoding apparatus 20 may obtain a (low-dimensionally converted) feature map and filtering information from a bitstream (S1910).
- the feature map may be a first feature map or first feature information.
- the feature decoding apparatus 20 may inversely transform the feature map to a higher dimension (S1920), and compensate for an error by filtering the feature map inversely transformed to a higher dimension (S1930) based on the filtering information.
- the feature decoding apparatus 20 may inverse quantize the filtered feature map (S1940).
- the inverse quantized feature map may be a second feature map or second feature information.
- processes S1930 and S1940 may be processes in which second feature information for 'inversely transformed first feature information' is derived based on the filtering information.
- Example 2-4 is a method of generating filtering information based on an extracted feature map and a feature map to which quantization, transformation, inverse transformation, and inverse quantization are applied.
- 20 is a flowchart illustrating a feature encoding method according to the embodiment 2-4
- FIG. 21 is a flowchart illustrating a feature decoding method according to the embodiment 2-4.
- the feature encoding apparatus 10 may extract a feature map from an image and quantize the extracted feature map (S2010). Also, the feature encoding apparatus 10 may transform the quantized feature map into a low-dimensional transform (S2020) and inverse transform the transformed feature map (S2030).
- S2020 low-dimensional transform
- S2030 inverse transform the transformed feature map
- the feature encoding apparatus 10 may inverse quantize the inversely transformed feature map (S2040).
- the feature encoding apparatus 10 may derive filtering information based on the inverse quantized feature map and the extracted feature map (S2050).
- the inverse quantized feature map may be a feature map that has undergone quantization, transformation, inverse transformation, and inverse quantization processes.
- the feature decoding apparatus 20 may obtain a (low-dimensionally converted) feature map and filtering information from a bitstream (S2110).
- the feature map may be a first feature map or first feature information.
- the feature decoding apparatus 20 may inversely transform the feature map into a high-dimensionality (S2120), and inversely quantize the high-dimensionally inversely transformed feature map (S2130). Also, the feature decoding apparatus 20 may compensate for an error by filtering the inversely quantized feature map based on the filtering information (S2140).
- the filtered feature map may be a second feature map or second feature information.
- Process S2140 may be a process of deriving second feature information for 'inversely transformed first feature information' based on the filtering information.
- Example 2-3 Comparing Example 2-3 with Example 2-4, while Example 2-3 derives filtering information through relatively few processes, Example 2-4 derives filtering information through additional processes. . Therefore, complexity can be reduced according to the embodiment 2-3, and filtering information can be more accurately derived according to the embodiment 2-4.
- filtering information (whether or not to apply filtering, filter parameters, etc.) necessary for the filtering process must be delivered to an element that performs filtering.
- the filtering information may be transferred to an element that performs filtering through an element that performs inverse transformation and an element that performs inverse quantization, or may be directly transferred to an element that performs filtering.
- Embodiment 3 is an embodiment of a method for signaling filtering information.
- the filtering information may include information indicating whether filtering is applied and information indicating filtering parameters.
- the feature encoding apparatus 10 may encode and signal information indicating whether filtering is applied and information indicating filtering parameters in feature units (or feature levels), and the feature decoding apparatus 20 may signal whether filtering is applied or not. It can be obtained in units of information features representing information and filtering parameters.
- the feature unit may be an individual feature channel or a set of feature channels. When similar feature channels are grouped and coded, filtering information can be shared, and compression efficiency can be improved.
- Table 1 shows an example in which filtering information is signaled in units of features.
- feature_ALF_flag is information indicating whether or not filtering is applied.
- a first value (e.g., 1) of feature_ALF_flag may indicate that filtering is applied, and a second value (e.g., 0) of feature_ALF_flag may indicate that filtering is not applied.
- can represent ALF_Param may be information indicating a filtering parameter.
- the feature encoding apparatus 10 may encode information indicating whether filtering is applied and information indicating a filtering parameter at a higher level than features and signal the encoding.
- the upper level may be a level including a plurality of features.
- the feature decoding apparatus 20 may obtain information indicating whether filtering is applied or not and a higher level indicating a filtering parameter.
- the upper level may be a level corresponding to a relatively large scale unit, such as a sequence parameter set (SPS), a picture parameter set (PPS), a picture header (PH), and a slice header (SH).
- SPS sequence parameter set
- PPS picture parameter set
- PH picture header
- SH slice header
- feature_ALF_flag is information indicating whether filtering is applied, and the first value (e.g., 1) of feature_ALF_flag may indicate that filtering is applied, and the second value (e.g., 0) of feature_ALF_flag is not applied filtering.
- ALF_Param may be information indicating a filtering parameter.
- feature_ALF_flag may be a first syntax element
- ALF_Param may be a second syntax element.
- ALF_Param may be signaled when feature_ALF_flag has a value indicating that filtering is applied.
- Exemplary methods of this disclosure are presented as a series of operations for clarity of explanation, but this is not intended to limit the order in which steps are performed, and each step may be performed concurrently or in a different order, if desired.
- other steps may be included in addition to the exemplified steps, other steps may be included except for some steps, or additional other steps may be included except for some steps.
- an image encoding device or an image decoding device that performs a predetermined operation may perform an operation (step) for confirming an execution condition or situation of the corresponding operation (step). For example, when it is described that a predetermined operation is performed when a predetermined condition is satisfied, the video encoding apparatus or the video decoding apparatus performs an operation to check whether the predetermined condition is satisfied, and then performs the predetermined operation. can be done
- the embodiments described in this disclosure may be implemented and performed on a processor, microprocessor, controller, or chip.
- functional units shown in each drawing may be implemented and performed on a computer, processor, microprocessor, controller, or chip.
- information for implementation e.g., information on instructions
- algorithm may be stored in a digital storage medium.
- a decoder (decoding device) and an encoder (encoding device) to which the embodiment(s) of the present disclosure are applied may be a multimedia broadcast transmission/reception device, a mobile communication terminal, a home cinema video device, a digital cinema video device, a surveillance camera, and a video conversation. device, real-time communication device such as video communication, mobile streaming device, storage medium, camcorder, video-on-demand (VoD) service providing device, OTT video (Over the top video) device, Internet streaming service providing device, 3-dimensional (3D) video device, VR (virtual reality) device, AR (argumente reality) device, video phone video device, transportation device (ex.
- real-time communication device such as video communication, mobile streaming device, storage medium, camcorder, video-on-demand (VoD) service providing device, OTT video (Over the top video) device, Internet streaming service providing device, 3-dimensional (3D) video device, VR (virtual reality) device, AR (argumente reality) device, video phone video device, transportation device (ex
- OTT video devices may include game consoles, Blu-ray players, Internet-connected TVs, home theater systems, smart phones, tablet PCs, digital video recorders (DVRs), and the like.
- the processing method to which the embodiment(s) of the present disclosure is applied may be produced in the form of a program executed by a computer and stored in a computer-readable recording medium.
- Multimedia data having a data structure according to the embodiment(s) of this document may also be stored in a computer-readable recording medium.
- the computer-readable recording medium includes all types of storage devices and distributed storage devices in which computer-readable data is stored.
- Computer-readable recording media include, for example, Blu-ray Disc (BD), Universal Serial Bus (USB), ROM, PROM, EPROM, EEPROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data
- a storage device may be included.
- a computer-readable recording medium includes media implemented in the form of a carrier wave (eg, transmission through the Internet).
- the bitstream generated by the encoding method may be stored in a computer-readable recording medium or transmitted through a wired or wireless communication network.
- embodiment(s) of the present disclosure may be implemented as a computer program product using program codes, and the program codes may be executed on a computer by the embodiment(s) of the present disclosure.
- the program code may be stored on a carrier readable by a computer.
- FIG. 22 is a diagram illustrating an example of a content streaming system to which embodiments of the present disclosure may be applied.
- a content streaming system to which an embodiment of the present disclosure is applied may largely include an encoding server, a streaming server, a web server, a media storage, a user device, and a multimedia input device.
- the encoding server compresses content input from multimedia input devices such as smart phones, cameras, camcorders, etc. into digital data to generate a bit stream and transmits it to a streaming server.
- multimedia input devices such as smart phones, cameras, and camcorders directly generate bitstreams
- the encoding server may be omitted.
- the bitstream may be generated by an image encoding method and/or an image encoding apparatus to which an embodiment of the present disclosure is applied, and the streaming server may temporarily store the bitstream while transmitting or receiving the bitstream.
- the streaming server transmits multimedia data to a user device based on a user's request through the web server, and the web server may serve as a medium informing the user of what kind of service is available.
- the web server transmits it to the streaming server, and the streaming server can transmit multimedia data to the user.
- the content streaming system may include a separate control server, and in this case, the control server may play a role of controlling commands/responses between devices in the content streaming system.
- a streaming server may receive content from a media store and/or an encoding server. For example, when receiving content from an encoding server, the content may be received in real time. In this case, in order to provide a smooth streaming service, the streaming server may store the bitstream for a certain period of time.
- Examples of user devices include mobile phones, smart phones, laptop computers, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), navigation devices, slate PCs, and tablets.
- PDAs personal digital assistants
- PMPs portable multimedia players
- PC tablet PC
- ultrabook wearable device (e.g., watch type terminal (smartwatch), glass type terminal (smart glass), HMD (head mounted display)), digital TV, desktop computer , digital signage, and the like.
- Each server in the content streaming system may be operated as a distributed server, and in this case, data received from each server may be distributed and processed.
- FIG. 23 is a diagram illustrating another example of a content streaming system to which embodiments of the present disclosure may be applied.
- the user terminal may perform the task according to the performance of the device, the user's request, the characteristics of the task to be performed, or the like, or an external device (e.g., streaming server, analysis server, etc.) You can also perform tasks in .
- a user terminal directly or through an encoding server provides a bitstream including information necessary for performing a task (e.g., information such as a task, a neural network, and/or a purpose). can be created through
- the analysis server may perform the requested task of the user terminal.
- the analysis server may transmit the result obtained through the task performance back to the user terminal or to another related service server (e.g., web server).
- the analysis server may transmit a result obtained by performing a task of determining fire to a fire-related server.
- the analysis server may include a separate control server, and in this case, the control server may serve to control commands/responses between each device associated with the analysis server and the server.
- the analysis server may request desired information from the web server based on task information that the user device wants to perform and tasks that can be performed.
- the web server When the analysis server requests a desired service from the web server, the web server transmits it to the analysis server, and the analysis server may transmit data about the service to the user terminal.
- the control server of the content streaming system may play a role of controlling commands/responses between devices in the streaming system.
- Embodiments according to the present disclosure may be used to encode/decode features/feature maps.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
Description
Claims (16)
- 피쳐(feature) 복호화 장치에 의해 수행되는 피쳐 복호화 방법으로서, 상기 피쳐 복호화 방법은,제1 피쳐 정보 및 상기 제1 피쳐 정보에 대한 필터링 정보를 비트스트림으로부터 획득하는 단계;상기 제1 피쳐 정보를 역변환하는 단계; 및상기 필터링 정보에 기반하여, 상기 역변환된 제1 피쳐 정보에 대한 제2 피쳐 정보를 유도하는 단계를 포함하는 피쳐 복호화 방법.
- 제1항에 있어서,상기 제2 피쳐 정보는 상기 역변환된 제1 피쳐 정보를 상기 필터링 정보에 기반하여 필터링함으로써 유도되는 피쳐 복호화 방법.
- 제1항에 있어서,상기 제2 피쳐 정보는 상기 역변환된 제1 피쳐 정보를 상기 필터링 정보에 기반하여 필터링하고, 상기 필터링된 제1 피쳐 정보를 역양자화하여 유도되는 피쳐 복호화 방법.
- 제1항에 있어서,상기 제2 피쳐 정보는 상기 역변환된 제1 피쳐 정보를 역양자화하고, 상기 역양자화된 제1피쳐 정보를 상기 필터링 정보에 기반하여 필터링함으로써 유도되는 피쳐 복호화 방법.
- 제1항에 있어서,상기 필터링 정보는 필터링의 적용 여부를 나타내는 제1 신택스 요소 및 상기 필터링의 파라미터를 나타내는 제2 신택스 요소를 포함하고,상기 제2 신택스 요소는 상기 제1 신택스 요소가 상기 필터링이 적용됨을 나타냄에 기반하여 획득되는 피쳐 복호화 방법.
- 제1항에 있어서,상기 필터링 정보는 상기 비트스트림의 피쳐 레벨로부터 획득되거나, 상기 비트스트림의 피쳐 레벨보다 상위 레벨로부터 획득되는 피쳐 복호화 방법.
- 피쳐(feature) 부호화 장치에 의해 수행되는 피쳐 부호화 방법으로서, 상기 피쳐 부호화 방법은,영상으로부터 추출된 피쳐 정보에 기반하여, 변환된 피쳐 정보를 유도하는 단계;상기 변환된 피쳐 정보에 기반하여, 역변환된 피쳐 정보를 유도하는 단계; 및상기 역변환된 피쳐 정보에 기반하여, 필터링 정보를 유도하는 단계를 포함하는 피쳐 부호화 방법.
- 제7항에 있어서,상기 필터링 정보는 상기 역변환된 피쳐 정보 및 상기 추출된 피쳐 정보에 기반하여 유도되는 피쳐 부호화 방법.
- 제7항에 있어서,상기 역변환된 피쳐 정보를 유도하는 단계는,상기 변환된 피쳐 정보를 부호화하고, 상기 부호화된 피쳐 정보를 복호화하는 단계; 및상기 복호화된 피쳐 정보를 역변환하여 상기 역변환된 피쳐 정보를 유도하는 단계를 포함하는 피쳐 부호화 방법.
- 제7항에 있어서,상기 변환된 피쳐 정보를 유도하는 단계는,상기 추출된 피쳐 정보를 양자화하는 단계; 및상기 양자화된 피쳐 정보를 변환하여 상기 변환된 피쳐 정보를 유도하는 단계를 포함하는 피쳐 부호화 방법.
- 제10항에 있어서,상기 필터링 정보를 유도하는 단계는,상기 역변환된 피쳐 정보를 역양자화하는 단계; 및상기 역양자화된 피쳐 정보에 기반하여 상기 필터링 정보를 유도하는 단계를 포함하는 피쳐 부호화 방법.
- 제10항에 있어서,상기 필터링 정보는 상기 양자화된 피쳐 정보 및 상기 역변환된 피쳐 정보에 기반하여 유도되는 피쳐 부호화 방법.
- 제7항에 있어서,상기 필터링 정보는 필터링의 적용 여부를 나타내는 제1 신택스 요소 및 상기 필터링의 파라미터를 나타내는 제2 신택스 요소를 포함하고,상기 제2 신택스 요소는 상기 필터링이 적용됨에 기반하여 상기 필터링 정보에 포함되는 피쳐 부호화 방법.
- 제7항에 있어서,상기 필터링 정보는 비트스트림의 피쳐 레벨에 부호화되거나, 상기 비트스트림의 피쳐 레벨보다 상위 레벨에 부호화되는 피쳐 부호화 방법.
- 제7항의 피쳐 부호화 방법에 의해 생성된 비트스트림을 저장하는 컴퓨터 판독 가능한 기록 매체.
- 피쳐 부호화 방법에 의해 생성된 비트스트림을 전송하는 방법으로서, 상기 피쳐 부호화 방법은,영상으로부터 추출된 피쳐 정보에 기반하여, 변환된 피쳐 정보를 유도하는 단계;상기 변환된 피쳐 정보에 기반하여, 역변환된 피쳐 정보를 유도하는 단계; 및상기 역변환된 피쳐 정보에 기반하여, 필터링 정보를 유도하는 단계를 포함하는 방법.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020247014027A KR20240090254A (ko) | 2021-09-29 | 2022-09-29 | 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 |
CN202280066198.6A CN118044203A (zh) | 2021-09-29 | 2022-09-29 | 特征编码/解码方法和装置以及存储比特流的记录介质 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202163250133P | 2021-09-29 | 2021-09-29 | |
US63/250,133 | 2021-09-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023055141A1 true WO2023055141A1 (ko) | 2023-04-06 |
Family
ID=85783270
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/014686 WO2023055141A1 (ko) | 2021-09-29 | 2022-09-29 | 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 |
Country Status (3)
Country | Link |
---|---|
KR (1) | KR20240090254A (ko) |
CN (1) | CN118044203A (ko) |
WO (1) | WO2023055141A1 (ko) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190117651A (ko) * | 2017-02-17 | 2019-10-16 | 코기센 에스.알.엘. | 이미지 프로세싱 및 비디오 압축 방법 |
US20210067785A1 (en) * | 2020-11-17 | 2021-03-04 | Intel Corporation | Video encoding rate control for intra and scene change frames using machine learning |
KR20210050186A (ko) * | 2019-10-28 | 2021-05-07 | 삼성전자주식회사 | 영상의 ai 부호화 및 ai 복호화 방법, 및 장치 |
US20210203997A1 (en) * | 2018-09-10 | 2021-07-01 | Huawei Technologies Co., Ltd. | Hybrid video and feature coding and decoding |
WO2021177652A1 (ko) * | 2020-03-02 | 2021-09-10 | 엘지전자 주식회사 | 피쳐 양자화/역양자화를 수행하는 영상 부호화/복호화 방법, 장치 및 비트스트림을 저장하는 기록 매체 |
-
2022
- 2022-09-29 KR KR1020247014027A patent/KR20240090254A/ko unknown
- 2022-09-29 CN CN202280066198.6A patent/CN118044203A/zh active Pending
- 2022-09-29 WO PCT/KR2022/014686 patent/WO2023055141A1/ko active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190117651A (ko) * | 2017-02-17 | 2019-10-16 | 코기센 에스.알.엘. | 이미지 프로세싱 및 비디오 압축 방법 |
US20210203997A1 (en) * | 2018-09-10 | 2021-07-01 | Huawei Technologies Co., Ltd. | Hybrid video and feature coding and decoding |
KR20210050186A (ko) * | 2019-10-28 | 2021-05-07 | 삼성전자주식회사 | 영상의 ai 부호화 및 ai 복호화 방법, 및 장치 |
WO2021177652A1 (ko) * | 2020-03-02 | 2021-09-10 | 엘지전자 주식회사 | 피쳐 양자화/역양자화를 수행하는 영상 부호화/복호화 방법, 장치 및 비트스트림을 저장하는 기록 매체 |
US20210067785A1 (en) * | 2020-11-17 | 2021-03-04 | Intel Corporation | Video encoding rate control for intra and scene change frames using machine learning |
Also Published As
Publication number | Publication date |
---|---|
CN118044203A (zh) | 2024-05-14 |
KR20240090254A (ko) | 2024-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020036417A1 (ko) | 히스토리 기반 움직임 벡터에 기반한 인터 예측 방법 및 그 장치 | |
WO2020071829A1 (ko) | 히스토리 기반 영상 코딩 방법 및 그 장치 | |
WO2020256344A1 (ko) | 영상 코딩에서 변환 커널 세트를 나타내는 정보의 시그널링 | |
WO2020189960A1 (ko) | 크로마 포맷에 대한 정보를 시그널링 하는 방법 및 장치 | |
WO2020149630A1 (ko) | 영상 코딩 시스템에서 cclm 예측 기반 영상 디코딩 방법 및 그 장치 | |
WO2020145604A1 (ko) | Mpm 리스트를 사용하는 인트라 예측 기반 영상 코딩 방법 및 장치 | |
WO2020141886A1 (ko) | Sbtmvp 기반 인터 예측 방법 및 장치 | |
WO2021040402A1 (ko) | 팔레트 코딩 기반 영상 또는 비디오 코딩 | |
WO2020256346A1 (ko) | 변환 커널 세트에 관한 정보에 대한 코딩 | |
WO2020145620A1 (ko) | Mpm 리스트를 사용하는 인트라 예측 기반 영상 코딩 방법 및 장치 | |
WO2020071832A1 (ko) | 변환 계수 코딩 방법 및 그 장치 | |
WO2020180043A1 (ko) | Lmcs에 기반한 영상 코딩 방법 및 그 장치 | |
WO2021137588A1 (ko) | 픽처 헤더를 포함하는 영상 정보를 코딩하는 영상 디코딩 방법 및 그 장치 | |
WO2021145726A1 (ko) | 적응적 루프 필터링 기반 영상 코딩 장치 및 방법 | |
WO2021137591A1 (ko) | Ols dpb 파라미터 인덱스를 포함하는 영상 정보 기반 영상 디코딩 방법 및 그 장치 | |
WO2020180044A1 (ko) | Lmcs에 기반한 영상 코딩 방법 및 그 장치 | |
WO2020256345A1 (ko) | 영상 코딩 시스템에서 변환 커널 세트에 관한 정보에 대한 컨텍스트 코딩 | |
WO2020071672A1 (ko) | 움직임 벡터를 압축하는 방법 및 그 장치 | |
WO2023055141A1 (ko) | 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 | |
WO2020060259A1 (ko) | 영상 코딩 시스템에서 블록 파티셔닝을 사용하는 영상 디코딩 방법 및 그 장치 | |
WO2024215142A1 (ko) | 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 | |
WO2023172090A1 (ko) | 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 | |
WO2023167502A1 (ko) | 피쳐 부호화/복호화 방법, 장치, 비트스트림을 저장한 기록 매체 및 비트스트림 전송 방법 | |
WO2023172014A1 (ko) | 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 | |
WO2024151061A1 (ko) | 채널 예측에 기반한 피쳐 부호화/복호화 방법, 장치 및 비트스트림을 저장한 기록 매체 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22876913 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280066198.6 Country of ref document: CN |
|
ENP | Entry into the national phase |
Ref document number: 20247014027 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 22876913 Country of ref document: EP Kind code of ref document: A1 |