Abstract: There are provided a method, apparatus, system, and computer-readable recording medium for image compression. An encoding apparatus performs domain transformation and quantization on feature map information and image information. The encoding apparatus rearranges the result of domain transformation and quantization so as to have a form advantageous to the encoding procedure and encodes the result of rearrangement, thereby generating a bitstream. A decoding apparatus receives the bitstream, decodes the received bitstream, and performs inverse transformation, dequantization, and inverse rearrangement using information transmitted through the bitstream. The result of inverse transformation, dequantization, and inverse rearrangement is used for the machine-learning task of a neural network.

Abstract: The present disclosure relates to a method and an apparatus for encoding multi plane image (MPI)-based volumetric video. A method for encoding a MPI-based volumetric video according to one aspect of the present disclosure may include: generating an MPI for each frame according to time change from a plurality of multi-viewpoint images; identifying a dynamic region and a static region within the MPI for each frame; generating a first atlas based only on the dynamic region and a second atlas based only on the static region; and encoding the first atlas and the second atlas to generate a bitstream, respectively.

Abstract: The present disclosure relates to a method and device for generating a voxel-by-voxel three-dimensional mesh texture patch. A method for generating a voxel-wise texture patch according to an embodiment of the present disclosure may comprise: generating a truncated signed distance function (TSDF) volume based on a multi-view image; generating and allocating a texture patch for each voxel in the TSDF volume; and performing optimization of the texture patch based on joint learning for the texture patch and a specific decoder to which the texture patch is input.

Abstract: Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding. An intra-prediction mode for the target block is derived, and intra-prediction for the target block that uses the derived intra-prediction mode is performed. The intra-prediction mode for the target block is derived using an artificial neural network, and an MPM list for the target block is derived using information about the target block, pieces of information about blocks adjacent to the target block, and the artificial neural network. The artificial neural network outputs one or more available intra-prediction modes. Further, the artificial neural network outputs match probabilities for one or more candidate intra-prediction modes, and each of the match probabilities for the candidate intra-prediction modes indicates a probability that the corresponding candidate intra-prediction mode matches the intra-prediction mode for the target block.

Abstract: An encoding/decoding method and device according to the present disclosure may: determine at least one among a plurality of inter prediction modes as the inter prediction mode of the current block; form an inter prediction candidate list on the basis of the determined inter prediction mode; perform motion compensation on the basis of one prediction candidate in the inter prediction candidate list, and generate a first prediction block of the current block; and correct the first prediction block by using a prescribed intra prediction mode.

Abstract: This disclosure provides a method and apparatus for compressing 3-dimensional volume data. The method for encoding a TSDF volume may comprise: lossily encoding magnitude information of a Truncated Signed Distance Field (TSDF) volume based on a hyperprior model; and losslessly encoding sign information of the TSDF volume based on the hyperprior model, wherein the lossy encoding comprises selecting and entropy-encoding some elements from a latent vector for the TSDF volume based on selection information obtained through the hyperprior model.

Abstract: The present disclosure relates to a method and apparatus for representing dynamic neural radiance fields from unsynchronized videos. A method of acquiring a video at an arbitrary viewpoint based on a dynamic neural radiance fields model according to an embodiment of the present disclosure may comprise: inputting one or more videos acquired from one or more views for one scene into the dynamic neural radiance fields model; inputting a time embedding for the one or more videos into the dynamic neural radiance fields model; and rendering the video at the arbitrary viewpoint based on color information and density information output by the dynamic neural radiance fields model. Herein, time synchronization related to the time embedding may be performed by applying an individual time offset learned for each view, for the one or more views.

Abstract: Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding. An intra-prediction mode for the target block is derived, and intra-prediction for the target block that uses the derived intra-prediction mode is performed. The intra-prediction mode for the target block is derived using an artificial neural network, and an MPM list for the target block is derived using information about the target block, pieces of information about blocks adjacent to the target block, and the artificial neural network. The artificial neural network outputs one or more available intra-prediction modes. Further, the artificial neural network outputs match probabilities for one or more candidate intra-prediction modes, and each of the match probabilities for the candidate intra-prediction modes indicates a probability that the corresponding candidate intra-prediction mode matches the intra-prediction mode for the target block.

Abstract: The present invention provides a method and device wherein segmentation information for a current picture is encoded/decoded, and the current picture is segmented into at least one of sub-picture units, slice units, and tile units according to the encoded/decoded segmentation information.

Abstract: There are provided an apparatus, method, system, and recording medium for performing selective encoding/decoding on feature information. An encoding apparatus generates residual feature information. The encoding apparatus transmits the residual feature information to a decoding apparatus through a residual feature map bitstream. The residual feature information is the difference between feature information extracted from an original image and feature information extracted from a reconstructed image. Feature information of the reconstructed image is generated using the reconstructed image. Reconstructed feature information is generated using the feature information of the reconstructed image and reconstructed residual feature information.

Abstract: An encoding/decoding method and device according to the present disclosure may: determine at least one among a plurality of inter prediction modes as the inter prediction mode of the current block; form an inter prediction candidate list on the basis of the determined inter prediction mode; perform motion compensation on the basis of one prediction candidate in the inter prediction candidate list, and generate a first prediction block of the current block; and correct the first prediction block by using a prescribed intra prediction mode.

Abstract: Disclosed herein are an image encoding/decoding method and apparatus. The image decoding method of the present disclosure may include obtaining maximum transform block size information, deriving a maximum transform block size on the basis of the maximum transform block size information, and, determining whether or not a secondary inverse transform is applied to the current block on the basis of the maximum transform block size and a horizontal size and a vertical size of a current block.

Abstract: An image encoding and decoding method comprises the steps of: determining an inter-component prediction mode of a chrominance component block on the basis of an inter-component prediction mode list and predetermined index information; determining a reference sample for inter-component prediction of the chrominance component block on the basis of the determined inter-component prediction mode; deriving the parameters of a linear prediction model by using the reference sample; and performing inter-component prediction for the chrominance component block by using the parameters of the linear prediction model.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding. In typical image encoding/decoding methods, a decoder-side motion information derivation method may be limitedly used. Therefore, the improvement of encoding efficiency attributable to the decoder-side motion information derivation method may also be limited. In embodiments, a motion information search method used in inter-prediction is disclosed. With the use of various motion search methods, encoding efficiency in inter-prediction may be improved.

Abstract: An image encoding/decoding method and apparatus are disclosed. The method of decoding an image according to the present invention, comprises, generating a first prediction block of a current block, generating a second prediction block of the current block and generating a final prediction sample of the current block using a sample unit weighted sum of the first prediction block and the second prediction block, wherein a weight used for the sample unit weighted sum is determined based on a location of a current luma sample and a geometric prediction mode (GPM) boundary line for partitioning the current block.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a binary mask. An encoding method includes generating a latent vector using an input image, generating a selected latent vector component set using a binary mask, and generating a main bitstream by performing entropy encoding on the selected latent vector component set. A decoding method includes generating a selected latent vector component set including one or more selected latent vector components by performing entropy decoding on a main bitstream and generating the latent vector in which the one or more selected latent vector components are relocated by relocating the selected latent vector component set in the latent vector.

Abstract: Disclosed herein is a video decoding method including determining a zero-out width threshold and a zero-out height threshold for distinguishing between a transform coefficient coding region and a zero-out region of a current block according to a size of the current block, determining the transform coefficient coding region and the zero-out region of the current block according to the zero-out width threshold and the zero-out height threshold, acquiring transform coefficient information of the transform coefficient coding region from a bitstream and determining a level of a transform coefficient of the transform coefficient coding region according to the transform coefficient information, determining a level of a transform coefficient of the zero-out region as 0 without acquiring transform coefficient information, and reconstructing the current block by inversely transforming the transform coefficient of the current block.

Abstract: The present invention provides a method and device wherein segmentation information for a current picture is encoded/decoded, and the current picture is segmented into at least one of sub-picture units, slice units, and tile units according to the encoded/decoded segmentation information.

Abstract: Disclosed therein are a method, an apparatus, and a storage medium for image encoding/decoding. Templating matching is used for prediction for a target block. Prediction information to be applied to encoding of the target block is determined, and prediction for the target block that uses the determined prediction information is performed. The prediction information includes a list and multiple candidates in the list. When the multiple candidates in the list are configured, template matching between blocks may be used. A candidate selected from among multiple candidates configured using template matching is used for prediction for the target block.

Abstract: An image encoding and decoding method comprises the steps of: determining an inter-component prediction mode of a chrominance component block on the basis of an inter-component prediction mode list and predetermined index information; determining a reference sample for inter-component prediction of the chrominance component block on the basis of the determined inter-component prediction mode; deriving the parameters of a linear prediction model by using the reference sample; and performing inter-component prediction for the chrominance component block by using the parameters of the linear prediction model.