Abstract: A method and apparatus for neural network based cross component prediction with scaling factors during encoding or decoding of an image frame or a video sequence, which may include training a deep neural network (DNN) cross component prediction (CCP) model with at least one or more scaling factors, wherein the at least one or more scaling factors are learned by optimizing a rate-distortion loss based on an input video sequence comprising a luma component, and reconstructing a chroma component based on the luma component using the trained DNN CCP model with the at least one or more scaling factors for chroma prediction. The trained DNN CCP may be updated for chroma prediction of the input video sequence using the one or more scaling factors, and performing chroma prediction of the input video sequence using the updated DNN CCP model with the one or more scaling factors.

Abstract: A method for visual media processing includes performing a conversion between a current video unit of a visual media data and a bitstream representation of the current video unit. The bitstream representation is configured according to a format rule. The format rule specifies a level of a video segment at which one or more syntax elements indicative of a scaling factor by which a chroma residual is scaled for coding the current video unit is selectively included in the bitstream representation.

Abstract: A method and apparatus for neural network based cross component prediction with low-bit precision during encoding or decoding of an image frame or a video sequence, which may include reconstructing a chroma component based on a received luma component using a pre-trained deep neural network (DNN) cross component prediction (CCP) model for chroma prediction, and updating a set of parameters of the pre-trained DNN CCP model with low-bit precision. The method may also include generating an updated DNN CCP model for chroma prediction with low-bit precision based on at least one video sequence, and using the updated DNN CCP model for cross component prediction of the at least one video sequence at reduced processing time.

Abstract: The present disclosure relates to a method for encoding a video stream. The method comprising: acquiring pixel data of the video stream having a first resolution; extracting a crop corresponding to a region of interest from the pixel data of the video stream, the crop having the first resolution; down-scaling the pixel data of the video stream into a down-scaled video stream having a second resolution lower than the first resolution; processing the down-scaled video stream through one or more video processing operations; processing the crop through the one or more video processing operations; up-scaling the processed down-scaled video stream into an up-scaled video stream having the first resolution; merging the processed crop and the up-scaled video stream into a merged video stream; and encoding the merged video stream. The present disclosure further related to a video encoding device.

Abstract: Methods, systems, and devices for picture output ordering constraints in video bitstreams are described. An example method of video processing includes performing a conversion between a video including one or more pictures and a bitstream of the video according to a rule, wherein the rule specifies that the bitstream includes at least a first picture that is output, wherein the first picture is in an output layer, wherein the first picture includes a syntax element equaling one, and wherein the syntax element affects a decoded picture output and a removal process associated with a hypothetical reference decoder (HRD).

Abstract: A computer-implemented method for operating an artificial neural network (ANN) includes receiving an input by the ANN. The ANN generates a latent representation of the input. The latent representation is communicated according to a bit rate based on a learned latent scaling parameter. The latent scaling parameter is learned based on a channel index and a tradeoff parameter value that corresponds to a value that balances the bit rate and a distortion.

Abstract: A method for video coding includes obtaining a coding block of video data, determining whether a joint coding of motion vector difference (JMVD) is used for predicting the coding block, obtaining, based on determining that the JMVD is used for predicting the coding block, a list of scaling factors and the JMVD from the video bitstream, deriving a predicted scaling factor based on the list of scaling factors, deriving a motion vector difference (MVD) for a reference list based on at least the joint motion vector difference and the predicted scaling factor, and reconstructing the coding block based on the derived MVD.

Abstract: This disclosure relates generally to video coding and particularly to cross component level reconstruction. For example, a method is disclosed for processing video data which may include extracting a first transform block of a first color component and a second transform block of a second color component from a bitstream of a video block; determining that transform coefficients in the first transform block are all zero; determining that a CCLR is applied to the first transform block; refining one or more of the transform coefficients in the first transform block, to obtain a refined first transform block; determining a target transform kernel for the refined first transform block; performing a reverse transform on the refined first transform block based on the target transform kernel to obtain a target block; and reconstructing the first color component of the video block based on at least the target block.

Abstract: An example device for decoding video data includes one or more processors implemented in circuitry and configured to: generate an inter-prediction block for a current block of video data; generate an intra-prediction block for the current block of video data; generate a final prediction block for the current block of video data from the inter-prediction block and the intra-prediction block, including performing each of combined inter/intra prediction (CIIP) mode, overlapped block motion compensation (OBMC), and luma mapping with chroma scaling (LMCS) while generating the final prediction block; and decode the current block of video data using the final prediction block. To generate the final prediction block, the processors may perform LMCS on a first inter-prediction sub-block, combine the LMCS-mapped first inter-prediction sub-block with the intra-prediction block using CIIP, and perform OBMC between the first CIIP prediction block and a second inter-prediction sub-block.

Abstract: An encoder includes circuitry and a memory coupled to the circuitry, wherein the circuitry, in operation, performs a partition process. The partition process includes calculating first values of a set of pixels between a first partition and a second partition in a current block, using a first motion vector for the first partition; calculating second values of the set of pixels, using a second motion vector for the second partition; and calculating third values of the set of pixels by weighting the first values and the second values. When a ratio of a width to a height of the current block is larger than 4 or a ratio of the height to the width of the current block is larger than 4, the circuitry disables the partition process.

Abstract: A processing circuitry decodes a plurality of maps in 2D from a bitstream carrying a mesh frame. The mesh frame represents a surface of an object with polygons. The plurality of maps includes a decoded geometry map and a decoded attribute map with an adaptive 2D atlas sampling applied. The processing circuitry determines at least a first sampling rate and a second sampling rate according to syntaxes signaled in the bitstream. The first sampling rate is applied to a first region of the mesh frame and the second sampling rate is applied to a second region of the mesh frame during the adaptive 2D atlas sampling. The processing circuitry reconstructs, based on the plurality of maps, at least a first vertex of the mesh frame according to the first sampling rate, and a second vertex of the mesh frame according to the second sampling rate.

Abstract: A surveillance system including a fixed camera and one or more temporary cameras and a control means coupled to the fixed camera and the one or more temporary cameras is disclosed. The control means is configured to extend coverage of the fixed camera using the one or more temporary cameras coupled to the fixed camera. Each of the one or more temporary cameras includes one or more sensors and is configured to be deployed and adjusted based on sensor data obtained from the one or more sensors of the one or more temporary cameras and from one or more fixed camera sensors co-located with the fixed camera.

Abstract: A method of encoding point cloud data includes signaling at least one of: a first syntax element indicating that planar mode is disabled for a current node when angular mode is enabled; or a second syntax element indicating that angular mode is enabled for the current node; bypassing signaling of values for a planar mode for the current node in a condition where the first syntax element indicates that the planar mode is disabled for the current node when the angular mode is enabled, or in a condition where the second syntax element indicates that the angular mode is enabled for the current node; and encoding the current node in a mode other than the planar mode.

Abstract: A three-dimensional data encoding method includes: calculating coefficient values from pieces of attribute information of three-dimensional points included in point cloud data; quantizing the coefficient values individually to generate quantized values; and generating a bitstream including the quantized values. Each of the coefficient values belongs to any one of layers. In the quantizing, each of the coefficient values is quantized using a quantization parameter for a layer to which the coefficient value belongs among the layers, and the bitstream includes first information and pieces of second information, the first information indicating a reference quantization parameter, the pieces of second information being for calculating quantization parameters for the layers from the reference quantization parameter.

Abstract: An apparatus includes a lens assembly that includes at least one lens that defines an optical axis, a lens holder coupled to the lens assembly, a substrate, an image sensor disposed on the substrate, and an actuator coupled between the lens holder and the substrate and configured to adjust a position of the substrate relative to the lens assembly to reposition the image sensor along the optical axis. The apparatus also includes a position sensor that includes a magnet and a magnetic field sensor. The position sensor is coupled to the substrate and the lens holder. The magnetic field sensor is configured to generate magnetic field data indicating a position of the substrate relative to the lens holder. The apparatus additionally includes circuitry configured to control the actuator based on the magnetic field data to place the image sensor within a depth of focus of the lens assembly.

Abstract: Devices, systems and methods for specifying the syntax and semantics of the decoding parameter set (DPS) are described. One example method of video processing includes determining, for a conversion between a video and a bitstream of the video, that each output layer set (OLS) in a coded video sequence (CVS) in the bitstream conforms to at least one profile-tier-level (PTL) syntax structure included in a data structure associated with decoding parameter semantics in the bitstream, and performing, based on the determining, the conversion, wherein the PTL syntax structure indicates a profile, a tier, and a level of the bitstream.

Abstract: Residual data is obtained based on first and second representations of an image at a first level of quality. The second representation is based on a representation of the image at a second, lower level of quality. The residual data is useable by a decoder to reconstruct the first representation using the second representation. A configuration message comprising a header part and a payload part is generated and output for processing by the decoder. The payload part comprises obtained configuration data relating to processing of the residual data. The header part comprises: (i) a message type parameter specifying a configuration message type and indicating a given payload format of the payload part, a format size of a payload part having said payload format is predetermined or can be determined from the content of the payload part, and (ii) a payload size parameter specifying the actual size of the payload part.

Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a first adaptation parameter set (APS) network abstraction layer (NAL) unit including an adaptive loop filter (ALF) type, a second APS NAL unit including a scaling list type, a third APS NAL unit including a luma mapping with chroma scaling (LMCS) type, and a slice. The mechanism further includes obtaining ALF parameters from the first APS NAL unit, obtaining scaling list parameters from the second APS NAL unit, and LMCS parameters from the third APS NAL unit. The mechanism further includes decoding the slice using the ALF parameters, the scaling list parameters, and the LMCS parameter. The mechanism further includes forwarding the slice for display as part of a decoded video sequence.

Abstract: A video encoding method includes: during a first period, performing an encoding process upon a first block group of a current frame to generate a first block group bitstream; and during a second period, transmitting a second block group bitstream derived from encoding a second block group of the current frame, wherein the second period overlaps the first period. The encoding process includes: during a first time segment of the first period, performing a first in-loop filtering process upon a first group of pixels; and during a second time segment of the first period, performing a second in-loop filtering process upon a second group of pixels, wherein the second time segment overlaps the first time segment, and a non-zero pixel distance exists between a first edge pixel of the first group of pixels and a second edge pixel of the second group of pixels in a filter direction.

Abstract: Provided are an image encoding/decoding method and device. An image decoding method performed by an image decoding device according to the present disclosure includes the steps of: determining a quantization parameter of the current block on the basis of whether color space conversion is applied to a residual sample of the current block; determining a transform coefficient of the current block on the basis of the quantization parameter; determining the residual sample of the current block by using the transform coefficient; and resetting the value of the residual sample on the basis of whether the color space conversion is applied.