84 results about "Interframe coding" patented technology

Methods and systems are described for end-to-end video coding and decoding using deep learning. Proposed fusion schemes for reference pictures and motion vector features allow single-prediction models for deep-learning video coding (DLVC) to be extended to support multi-reference prediction coding as well. Example high-level syntax to support a variety of deep learning models for bi-prediction is described as well.

This invention discloses a bitrate control method at the image block level for P-frames and / or B-frames. Step S1: Obtain the inter-frame coding mode candidates and their prediction costs for each image block to be encoded. Step S2: Select the minimum prediction cost to characterize the inter-frame coding complexity of the image block to be encoded; use the sum of the inter-frame coding complexities of all image blocks within a video frame as the inter-frame coding complexity of that video frame. Step S3: Calculate the target number of coding bits for each image block to be encoded within the P-frame or B-frame to be encoded. Step S4: Calculate the Lagrange multipliers for the image block to be encoded within the P-frame or B-frame to be encoded. Step S5: Perform video encoding on the image block to be encoded, and then adjust the target number of coding bits for the next image block to be encoded within the P-frame or B-frame to be encoded. This invention has low hardware overhead and low implementation cost; it does not introduce a large number of complex floating-point operations, reducing the difficulty and cost of hardware implementation.

A method and apparatus for padding out-of-boundary pixels are disclosed. According to the method, input data associated with a current block located at or near a picture boundary are received, wherein the input data comprise prediction data and reconstructed residual data related to the current block. An extended motion-compensated reconstructed block for the current block is generated based on the prediction data and the reconstructed residual data, wherein the extended motion-compensated reconstructed block for the current block is inter coded and comprises a padded area located outside the picture boundary and a reconstructed current block. At least one in-loop filter is applied to the extended motion-compensated reconstructed block.

The present invention discloses an image decoding method. Error report information related to an error block in an N-th image frame generated according to an inter-frame coding technology is received by an image encoding apparatus when the image decoding apparatus receives a block of an N+P−1-th image frame. The N+P-th image frame is encoded according to the inter-frame coding technology. Blocks in the N-th image frame before the error block are decoded according to the inter-frame coding technology. A panning motion vector of an N−1-th image frame serves as the motion vector information and the residue information is set to be zero to decode the blocks from the error block to the N+P−1-th image frame according to the inter-frame coding technology. The motion vector information and the residue information of the inter-frame coding blocks in the N+P-th image frame are retrieved to perform decoding according to the inter-frame coding technology.

Motion compensation requires a significant amount of memory bandwidth, especially for smaller prediction unit sizes. The worst case bandwidth requirements can occur when bi-predicted 4×8 or 8×4 PUs are used. To reduce the memory bandwidth requirements for such smaller PUs, methods are provided for restricting inter-coded PUs of small block sizes to be coded only in a uni-predictive mode, i.e., forward prediction or backward prediction. More specifically, PUs of specified restricted sizes in bi-predicted slices (B slices) are forced to be uni-predicted.

This application provides a video decoding method, a video encoding method, and a computer-readable storage medium. Video encoding and decoding techniques for bidirectional prediction with weighted averaging are disclosed. According to some embodiments, a computer-implemented video decoding method includes the following steps: decoding a bitstream associated with a target coding block; reconstructing the target coding block based on a merge candidate list, the merge candidate list including one or more merge candidates associated with one or more inter-frame coding blocks other than the target coding block, each of the one or more merge candidates being motion information associated with the corresponding inter-frame coding block, wherein at least one of the one or more merge candidates includes bidirectional prediction weights.

A block vector (BV) of an intra-coded and / or inter-coded block may be used for building a BV candidate list. A device may generate a candidate list(s) for a current block. The device may determine a neighboring block to the current block is intra-coded and / or inter-coded. The device may determine a BV is associated with the neighboring block. The device may, e.g., on condition that the neighboring block is intra-coded and the BV is associated with the neighboring block, add the BV to the at least one candidate list. The device may, e.g., on condition that the neighboring block is inter-coded and the BV is associated with the neighboring block, add the BV to the at least one candidate list. The device may, e.g., on condition that the neighboring block is intra-coded and / or inter-coded, and the BV is associated with the neighboring block, add the BV to the candidate list.

The present application discloses a video coding method, system, apparatus, and device. The method utilizes the inter-coding mode information of neighboring CUs of a target coding unit and employs a weighted scoring mechanism for voting by neighboring CUs to make decisions on skipping the inter-coding mode of the target coding CU. This early termination of inter-coding mode decisions allows for rapid selection of merge mode or skip mode as the optimized inter-coding mode, and premature termination of the time-consuming search process for inter-coding and other modes. This effectively reduces the complexity of inter-coding for large-sized CUs, thereby improving overall coding efficiency.

Systems, methods, and instrumentalities are disclosed for constructing a template-based intra mode derivation (TIMD) merge mode from collocated block. Based on the determination that the collocated block of the previous inter-coded frame is coded in TIMD mode, TIMD information associated with the collocated block may be obtained. TIMD merge list may be generated based on at least the TIMD information associated with the collocated block. A TIMD candidate may be selected from the TIMD merge list for decoding a current block of a current inter-coded frame. The current block of the current inter-coded frame may be decoded based on the selected TIMD candidate.

An aspect of the disclosure provides a method of video decoding. For example, a coded video bitstream is received. The coded video bitstream includes coded information of a plurality of pictures. Based on the coded information, a current block in a current picture is determined to be coded using an inter prediction mode, prediction samples of the current block in the inter prediction mode are generated at least partially based on a reference block in a reference picture that is different from the current picture. Also, intra prediction mode associated with the current block in the current picture is obtained. One or more transform kernels are determined based on the intra prediction mode associated with the current block. The current block is reconstructed based on the one or more transform kernels.

The invention discloses an early termination method and device for inter-frame coding segmentation, equipment and a storage medium. The method comprises the following steps: calculating a feature distance between to-be-segmented regions based on coding block features; inputting the feature distance into a pre-trained neural network classification model for segmentation threshold prediction, and outputting a target segmentation threshold of the target coding block; based on the feature distance and the target segmentation threshold, judging whether the target coding block meets a segmentation termination condition or not; and if yes, stopping segmentation of the target coding block. According to the embodiment of the invention, features highly related to CU segmentation are selected by using a machine learning algorithm, features having the greatest influence on a segmentation decision are selected by analyzing texture and depth map information of the CU, and early termination of CU segmentation of a texture video and a depth map is realized based on a threshold value extracted from a training model.

An apparatus directed to improvements to motion coding for vertices in an inter-coded base mesh frame is provided. The apparatus receives a compressed bitstream comprising a base mesh sub-bitstream and a syntax element. The apparatus decodes the syntax element to generate a prediction error. The apparatus decodes the base mesh sub-bitstream to generate a base mesh frame. The apparatus determines neighboring vertices of a vertex based on the base mesh frame. The apparatus determines a first predictor based on the neighbors of the vertex. The apparatus determines the vertex based on the first predictor and the prediction error.

Methods, apparatus, and non-transitory computer-readable storage media for video decoding and encoding are provided. In a video decoding method, a decoder may obtain a target motion vector of a current interframe coding block from a candidate list based on a plurality of first reconstruction sample points adjacent to the current interframe coding block, the candidate list including a plurality of motion vector candidates of the current interframe coding block; obtaining a plurality of first prediction sample points based on the target motion vector of the current inter-frame coding block; and in response to determining that adaptive motion compensation filtering is applied to the current inter-coded block, obtaining a plurality of filtered prediction samples based on the at least one template filter and the plurality of first prediction samples.

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, usage information of a plurality of template-based approaches is determined for the current video block based on at least one syntax element at a first level. The first level is higher than a coding unit level. The conversion is performed based on the usage information. The plurality of template-based approaches comprises at least two coding tools associated with at least one of: intra coding, inter coding, or intra block copy (IBC) coding.

This application provides a video encoding method and system based on screen sharing. The method includes: when a first terminal device is detected to start or a new scene appears, video encoding is performed at a corresponding first moment using quantization parameter values; during a period of time after the first moment, while the scene remains unchanged, the quantization parameter values ​​are adjusted; when the quantization parameter values ​​reach a first preset threshold, a long-term reference frame group is constructed based on the corresponding image frames; when a scene switch is detected in the first terminal device, it is determined whether there is a reference frame in the long-term reference frame group that meets preset conditions; if so, the current frame to be encoded is encoded based on the reference frame using a combination of inter-frame coding and intra-frame coding to obtain encoded data; and the encoded data is sent to a second terminal device for decoding. This application can avoid network congestion when a scene switch occurs during screen sharing.

Disclosed herein are systems, methods, and instrumentalities associated with dual tree coding modes and chroma intra prediction modes reordering. A video coding device as described herein may determine whether a chroma video block is located in an intra-coded region of an inter-coded video slice. Based at least on a determination that the chroma video block is located in the intra-coded region of the video slice and a further determination that a dual tree partition mode is enabled for the intra-coded region, the video coding device may be further configured to determine a plurality of intra prediction modes for the chroma video block, calculate, for each of plurality of intra prediction modes, a respective combined cost associated with predicting the chroma video block and a luma video block co-located with the chroma video block using the intra prediction mode, and reorder the plurality of intra prediction modes based on the respective combined cost calculated for each of the plurality of intra prediction modes. The video coding device may then code the chroma video block based on the reordering of the plurality of intra prediction modes.

This disclosure provides methods, devices, and systems for video coding. The present implementations more specifically relate to hybrid coding techniques that combine aspects of inter-frame coding with aspects of intra-frame coding. In some aspects, a video encoder may perform inter-frame coding in a weighted manner so that the coded video frames (also referred to as “residual frames”) may include contributions from the current video frame to be transmitted over a communication channel and also may include contributions from the previous video frame transmitted over the communication channel. More specifically, any pixel value (r(n)) in the residual frame can be expressed as a weighted combination of a respective pixel value (x(n)) in the current video frame and a co-located pixel value (x(n−1)) in the previous video frame, where r(n)=x(n)−α·x(n−1) and where 0≤α≤1 is a scaling factor representing the degree of contribution by the previous video frame.

The invention provides a video coding method and device, equipment and a storage medium, and belongs to the field of image processing, and the method comprises the steps: in a video coding process, obtaining a target quantization parameter corresponding to a current to-be-coded image frame in a video based on a first reference frame of a target frame number obtained each time during inter-frame coding, the target quantization parameter is smaller than a quantization parameter adopted for encoding the first reference frame; and performing inter-frame coding on the current to-be-coded image frame according to the target quantization parameter to obtain a second reference frame until video coding is completed. According to the method, the high-quality reference frame is inserted during inter-frame coding, so that the video quality of the whole video can be effectively improved, and the video watching experience of a user is improved.

Systems and methods for encoding data for low-latency streaming are disclosed herein. The system encodes a plurality of frames of a video. The encoded frames of the video comprise at least one intra-coded key frame and at least one inter-coded frame. A subset of the plurality of encoded frames, along with a corresponding identifier for each frame in the subset, is added to a reference frame data structure. The system encodes a first frame as a first inter-frame referencing at least one encoded frame from the data structure and determines, based at least in part on properties of a stream, a probability of the first inter-frame being dropped during at least one of transmission or decoding. Based on the calculated probability, the system omits the first inter-frame from the data structure and encodes a second frame subsequent to the first frame using the data structure that omits the first inter-frame.

The application provides a video coding method and system based on screen sharing, the method comprising: in the case of detecting that a first terminal device starts or a new scene occurs, coding a video at a corresponding first time with a quantization parameter value; in the case of a time period after the first time and the scene remaining unchanged, adjusting the quantization parameter value; in the case of the quantization parameter value reaching a first preset threshold, constructing a long-term reference frame group based on a corresponding image frame; in the case of detecting that the first terminal device undergoes scene switching, judging whether a reference frame meeting a preset condition exists in the long-term reference frame group; if so, coding a current frame to be coded in a manner combining inter-frame coding and intra-frame coding based on the reference frame to obtain coding data; and sending the coding data to a second terminal device for decoding; the application can avoid the occurrence of network congestion in the case of screen sharing scene switching.

The present disclosure relates to an inter-frame coding motion vector processing method and apparatus. The method includes: acquiring an estimated motion vector between a current coded image block and a reference frame coded image block and a position number of the estimated motion vector; reading merge motion vector information corresponding to the position number from a target merge table according to the position number of the estimated motion vector; the target merge table including a relationship between position numbers of estimated motion vectors and merge motion vector information corresponding to the position numbers of the estimated motion vectors; and replacing the estimated motion vector corresponding to the 10 position number with the merge motion vector information, and coding the merge motion vector information. By use of the method, the time of deciding a candidate motion vector in a video inter-frame coding merge mode can be reduced, thereby improving computing efficiency.

At least one method and apparatus for efficient encoding or decoding of video is presented. For example, motion information representing camera motion between a current image and a reference image is determined, where the current image and the reference image are part of a game engine 2D rendered video. For example, motion information of at least one sample in a coded block of a current image inter-coded with respect to a reference image is determined based on a depth model and camera parameters of the coded block. For example, at least one parameter of a depth model of an encoded block is obtained, where the depth model comprises a plane representing depth values. Camera motion information is used in encoding or decoding of a block.

The application provides an image coding method and device. The image coding method comprises the following steps: obtaining an image to be coded, the image to be coded is divided into a basic layer and at least one enhancement layer; when receiving feedback information sent by a decoding end, determining a reconstructed image corresponding to a frame number and a layer number indicated in the feedback information as a first reference frame, and performing interframe coding on the basic layer according to the first reference frame to obtain a code stream of the basic layer; respectively coding the at least one enhancement layer to obtain code streams of the at least one enhancement layer; and sending the code stream of the basic layer and the code streams of the at least one enhancement layer to the decoding end, wherein the code stream of the basic layer carries coding reference information. The application can improve the quality or resolution of a current image frame.

This disclosure provides a video decoding method. For example, receiving an encoded video stream. The encoded video stream includes encoded information from multiple images. Based on the encoded information, determining that a current block in the current image is encoded using an inter-frame prediction mode, and generating prediction samples of the current block in the inter-frame prediction mode based at least in part on reference blocks in a reference image different from the current image. Furthermore, obtaining an intra-frame prediction mode associated with the current block in the current image. Determining at least one transform kernel based on the intra-frame prediction mode associated with the current block. Reconstructing the current block based on the at least one transform kernel.

The invention discloses a dynamic picture file processing method and device, equipment and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: obtaining a dynamic picture file containing a dynamic picture track and a static picture data item; and determining a target image frame in the dynamic picture track and coding characteristics and coding types of the target image frame. If the coding characteristic is intra-frame coding or inter-frame coding and the coding type is an intra-frame coding image, keeping the media data of the target frame in a dynamic picture track, setting metadata in a static picture data item, establishing an incidence relation and obtaining a first packaging result, and if the coding characteristic is inter-frame coding and the coding type is an inter-frame coding image, keeping the media data of the target frame in the dynamic picture track, and setting metadata in the static picture data item and establishing an incidence relation to obtain a second packaging result; and if not, recoding the target frame, and storing the media data into a file independent of the track to obtain a second packaging result. The target presentation picture and the packaging result type thereof are determined according to user requirements, and the picture is presented in a corresponding mode, so that the dynamic picture file processing efficiency is improved.

Embodiments of the present application provide a point cloud data encoding and decoding method, device, computer equipment and readable storage medium. The encoding method comprises: obtaining a to-be-encoded sub-node in point cloud data; obtaining a prediction encoding state of the to-be-encoded sub-node; wherein the prediction encoding state comprises an inter-frame encoding state and an intra-frame encoding state; determining a first context probability model corresponding to the to-be-encoded sub-node based on the prediction encoding state; and encoding the occupancy information of the to-be-encoded sub-node through the first context probability model to obtain target encoding data of the occupancy information. In this way, the corresponding first context probability model can be accurately determined by effectively utilizing the prediction encoding state, and the accuracy of encoding the to-be-encoded sub-node of the point cloud data is improved.

Methods, systems, and bitstream syntax are described for inter-frame coding using end-to-end neural networks used in image and video compression. Inter-frame coding methods include one or more of: joint luma-chroma motion compensation for YUV pictures, joint luma-chroma residual coding for YUV pictures, using attention layers, enabling temporal motion prediction networks for motion vector prediction, using a cross-domain network which combines motion vector and residue information for motion vectors decoding, using the cross-domain network for decoding residuals, using weighted motion-compensated inter prediction, and using temporal only, spatial only, or both temporal and spatial features in entropy decoding. Methods to improve training of neural networks for inter-frame coding are also described.

An apparatus includes processing circuitry that is configured to receive a bitstream including coded information of a current block. The processing circuitry is configured to partition the current block into a first partition and a second partition based on a geometric partition mode (GPM). The processing circuitry is configured to determine a first prediction mode for the first partition based on a first number of direct neighboring reconstructed samples of the current block being larger than a threshold value. The processing circuitry is configured to, when the first number of direct neighboring reconstructed samples of the current block is less than the threshold value, infer that the first prediction mode is inter prediction mode, a flag indicating whether the current block is intra coded or inter coded not being signaled in the bitstream, and reconstruct the first partition of the current block based on the first prediction mode.

Systems, methods, and instrumentalities associated with video coding (e.g., encoding and decoding) are disclosed herein. A video encoding apparatus or a video decoding apparatus according to the present disclosure may acquire an inter-coded video block associated with a current picture and divide the inter-coded video block into at least a first sub-partition and a second sub-partition. The video encoding apparatus or video decoding apparatus may reconstruct the first sub-partition based on a first motion vector associated with the inter-coded video block, determine a second motion vector based on the first motion vector and one or more reconstructed samples of the first sub-partition, and reconstructing the second sub-partition based on the second motion vector.