Abstract: An image encoding apparatus includes: at least one processor configured to implement: a text adaptation module configured to generate relevance information indicating a relevance between an image feature and a text feature based on text caption information corresponding to an original image; and an encoding module configured to generate a latent representation which represents the text caption information and the image feature using the relevance information and the original image, wherein the text adaptation module is further configured to communicate with the encoding module while generating the relevance information.

Abstract: This disclosure relates generally to video coding and particularly to intra block copy coding mode. For example, a method is disclosed for reconstructing a video block in a video stream. The method may include extracting at least one syntax element from the video stream, the at least one syntax element being associated with an intra block copy (IBC) prediction of the video block; determining an IBC referencing mode for the IBC prediction of the video block, the IBC referencing mode comprises one of no-IBC mode, a local-referencing IBC mode, a non-local-referencing IBC mode, and a local-and-non-local-referencing IBC mode; and generating reconstructed samples of the video block from the video stream based on the IBC referencing mode.

Abstract: In a three-dimensional (3D) display, an optical element is arranged on an optical path of an array of light-emitting elements. A region of the array to be employed to display a graphical element to a given eye is determined, based on a position of the graphical element within a 3D view frustum. A sample map indicating perceived shapes, perceived sizes and relative perceived positions of light-emitting elements in at least said region is generated from a perspective of the given eye, based on a relative location of the given eye with respect to an image plane and on optical distortion parameters of the optical element. A shape of the graphical element is adjusted while selecting a set of light-emitting elements from said region for displaying the graphical element, based on the sample map. This set is employed for displaying the graphical element to the given eye.

Abstract: Systems and methods for video coding on regions of interest are provided. In some embodiments, the methods and systems for improved ROI treatment of a coded video frame includes blocking a video frame into blocks. Next a region of interest (ROI) level to each of the blocks is assigned. This ROI assignment process may include determining variance for each block, grouping blocks by similar variance, detecting motion for each block and assigning the ROI level responsive to the variance and presence of motion for the given block. Lastly, a quantization parameter (QP) level is assigned to each block responsive to the ROI level for the given block. In some cases, the ROI level assigned to a block is responsive to a bounding box being present. The bounding box is generated responsive to an algorithm identifying an object of interest (e.g., a face).

Abstract: According to the present disclosure, a method by which a decoding device decodes an image comprises the steps of: acquiring a bit-stream including image information; deriving a decoder-side intra mode derivation (DIMD) mode for the current block; deriving an intra-prediction mode for the current block; generating prediction samples for the current block on the basis of the intra-prediction mode for the current block; and generating reconstructed samples for the current block on the basis of the prediction samples for the current block, wherein the intra-prediction mode for the current block is derived on the basis of whether the DIMD mode is applied to the current block.

Abstract: Systems, devices, and methods of Fourier ptychographic imaging by computationally reconstructing a high-resolution image by iteratively updating overlapping regions of variably-illuminated, low-resolution intensity images in Fourier space.

Abstract: A method and apparatus for video coding are disclosed. According to the method for the decoder side, a first syntax, related to whether the current block is coded in a CCLM related mode, is parsed from a bitstream comprising the encoded data for the current block. If the first syntax indicates the current block being coded in the CCLM related mode, a second syntax is parsed from the bitstream, wherein the second syntax is related to whether a multiple model CCLM mode is used or whether one or more model parameters are explicitly signalled or implicitly derived. The model parameters for the second-colour block are determined if the first syntax indicates the current block being coded in a CCLM related mode. The encoded data associated with the second-colour block is then decoded using prediction data comprising the cross-colour predictor for the second-colour block.

Abstract: A signal processing apparatus includes one or more memories configured to store instructions, and one or more processors configured to execute the instructions to acquire first time information, perform signal processing on an acoustic signal to generate first acoustic data including the acquired first time information, measure processing time for the signal processing based on the acquired first time information and the first acoustic data, acquire second time information indicating a time after measuring the processing time, perform signal processing on the acoustic signal to generate second acoustic data that does not include the first time information and the acquired second time information, correct the second time information based on the processing time, and record the second acoustic data synchronized in time with the corrected second time information.

Abstract: A method of decoding a coded video bitstream includes obtaining a reference picture list structure for a current slice represented in the coded video bitstream, wherein the reference picture list structure contains a number of entries; obtaining a default number of active entries in a reference picture list for the current slice; constructing a reference picture list for the current slice, the reference picture list containing a number of active and inactive entries; setting the number of active entries in the reference picture list equal to the number of entries in the reference picture list structure when the default number of active entries in the reference picture list is greater than the number of entries in the reference picture list structure; and obtaining, based on at least one active entry of the reference picture list, at least one reconstructed block of the current slice.

Abstract: Example devices, methods, and computer-readable media are disclosed for decoding video data. An example method includes determining to decode a current block of the video data using a merge mode. The example method includes obtaining a flag from a bitstream. The example method includes determining, based on a value of the flag, to use a second merge list of two merge lists for the current block, wherein the second merge list is based on a first merge list of the two merge lists. The example method includes decoding the current block based on the second merge list.

Abstract: In a method and device for signaling of DRX configuration, the method for a first UE includes the steps of: receiving, from a second UE, signaling message #1 including second Uu DRX configuration information for a second Uu link between the second UE and a second base station; reconfiguring SL DRX configuration information for an SL DRX operation in consideration of the second Uu DRX configuration information, such that the SL DRX operation for SL between the first UE and the second UE and a second Uu DRX operation for the second Uu link are aligned; and transmitting, to the second UE, signaling message #2 including the reconfigured SL DRX configuration information.

Abstract: A video decoding method comprises: deriving L0 and L1 motion vectors of a current block; deriving decoder-side motion vector refinement (DMVR) flag information indicating whether to apply a DMVR to the current block; when the DMVR flag information indicates that the DMVR is to be applied to the current block, deriving refined L0 and L1 motion vectors based on the L0 and L1 motion vectors by applying the DMVR to the current block; deriving prediction samples of the current block based on the refined L0 and L1 motion vectors; and generating reconstructed samples of the current block based on the predicted samples, wherein deriving DMVR flag information comprises deriving the DMVR flag information by applying the DMVR to the current block when the height of the current block is 8 or more, and when the values of L0 and L1 luma weighted prediction flag information are both 0.

Abstract: A three-dimensional data encoding method includes: obtaining three-dimensional points; generating a data unit including one or more prediction trees and one or more identification information items, using the three-dimensional points; and generating a bitstream including the data unit. The data unit includes one identification information item out of the one or more identification information items subsequent to one prediction tree out of the one or more prediction trees, and the one identification information item indicates whether there is a subsequent prediction tree subsequent to the one identification information item in the data unit.

Abstract: A video decoding method performed by a video decoding device according to the present document comprises the steps of: acquiring image information from a bitstream, the image information including a picture header associated with the current picture including a plurality of slices; parsing, from the picture header, a first flag indicating whether information necessary for an inter-prediction operation for a decoding process is present in the picture header; parsing, from the picture header, a second flag indicating whether information necessary for an intra-prediction operation for the decoding process is present in the picture header; and generating prediction samples by performing at least one of intra-prediction or inter-prediction for the slices in the current picture on the basis of the first flag or the second flag.

Abstract: The present disclosure relates to a method for decoding a video signal based on adaptive multiple transforms (AMT). The method includes: obtaining an AMT index from the video signal, where the AMT index indicates any one of a plurality of transform combinations in a transform configuration group, and the transform configuration group includes discrete sine transform type 7 (DST7) and discrete cosine transform type 8 (DCT8); deriving a transform combination corresponding to the AMT index, where the transform combination includes a horizontal transform and a vertical transform, and at least one of the DST-7 or the DCT-8; performing an inverse transform on a current block on the basis of the transform combination; and restoring the video signal by using the inversely transformed current block. The AMT represents a transform scheme that is performed based on a transform combination adaptively selected from a plurality of transform combinations.

Abstract: Aspects of the disclosure includes methods and apparatuses for video decoding and video encoding and a method of processing visual media data. A current block in a first coding tree unit (CTU) is predicted using samples in a current picture. The first CTU and a second CTU are processed in parallel. The method for video decoding includes determining one of (i) a reference block of the current block in an allowed search range that is constrained for parallel processing of the first CTU and the second CTU in the current picture and (ii) an intra prediction mode of the current block based on a template adjacent to the current block that is constrained for parallel processing of the first CTU and the second CTU, and reconstructing the current block using the one of (i) the reference block and (ii) the intra prediction mode.

Abstract: Apparatuses and methods for displaying a 3-D representation of an object are described. Apparatuses can include a rotatable structure, motor, and multiple light field sub-displays disposed on the rotatable structure. The apparatuses can store a light field image to be displayed, the light field image providing multiple different views of the object at different viewing directions. A processor can drive the motor to rotate the rotatable structure and map the light field image to each of the light field sub-displays based in part on the rotation angle, and illuminate the light field sub-displays based in part on the mapped light field image. The apparatuses can include a display panel configured to be viewed from a fiducial viewing direction, where the display panel is curved out of a plane that is perpendicular to the fiducial viewing direction, and a plurality of light field sub-displays disposed on the display panel.

Abstract: An image decoding method includes a step of deriving a residual sample, wherein the step of deriving the residual sample includes the steps of: when a current block is divided into sub-partition blocks, deriving a transform kernel for an inverse primary transform applied to a sub-partition block based on a horizontal or a vertical length of the sub-partition block; and deriving the residual sample from transform coefficients based on the transform kernel.

Abstract: This disclosure relates to signaling, parsing, and using adaptive resolution for motion vector difference in video coding. An example method includes receiving a video bitstream and extracting an inter-prediction syntax element from the video bitstream. The inter-prediction syntax element indicates which single-reference inter-prediction mode is enabled for one or more video blocks of the video bitstream. The method further includes determining whether an adaptive motion vector difference (MVD) mode is enabled for the one or more video blocks. The adaptive MVD mode is a single-reference inter-prediction mode with an adaptive MVD pixel resolution. When the adaptive MVD mode is enabled for the one or more video blocks, the method includes selecting a current MVD pixel resolution from a set of available MVD pixel resolutions. The method also includes decoding the one or more video blocks based on the current MVD pixel resolution.

Abstract: An example method of decoding an encoded video bitstream using at least one processor includes obtaining an encoded video bitstream, the encoded video bitstream including encoded color components. The method also includes entropy parsing the encoded color components and dequantizing the color components and obtaining transform coefficients of the color components. The method further includes applying a joint components secondary transform (JCST) on the transform coefficients of the color components, thereby generating JCST outputs. The method also includes performing a backward transform on the JCST outputs, thereby obtaining residual components of the color components; and decoding the encoded video bitstream based on the residual components of the color components.