Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

10386 results about "Video encoding" patented technology

In video editing and production video encoding is the process of preparing the video for output, where the digital video is encoded to meet proper formats and specifications for recording and playback through the use of video encoder software. Also called video conversion. See also encoding.

Systems and methods for coding and decoding image data using general adversarial models

A video encoder and decoder system employing a compression-decision generative adversarial model (“CDGAM”) has an encoder with a compression network and a decoder with a task network. The compression network is a generator portion of a pretrained CDGAM and the task network is a discriminator portion of the pretrained CDGAM. The compression network and task network are trained using common image data wherein the compression network is trained to a generate minimal compressed representation that results in a substantially similar loss as the original image at the discriminator.
Owner:OP SOLUTIONS

Systems and methods for generalized multi-hypothesis prediction for video coding

Systems and methods are described for video coding using generalized bi-prediction. In an exemplary embodiment, to code a current block of a video in a bitstream, a first reference block is selected from a first reference picture and a second reference block is selected from a second reference picture. Each reference block is associated with a weight, where the weight may be an arbitrary weight ranging, e.g., between 0 and 1. The current block is predicted using a weighted sum of the reference blocks. The weights may be selected from among a plurality of candidate weights. Candidate weights may be signaled in the bitstream or may be derived implicitly based on a template. Candidate weights may be pruned to avoid out-of-range or substantially duplicate candidate weights. Generalized bi-prediction may additionally be used in frame rate up conversion.
Owner:INTERDIGITAL VC HOLDINGS INC

Video encoding method, apparatus and device, video decoding method, apparatus and device, video encoding and decoding system, and storage medium

A video decoding method, including: obtaining a first index by decoding a bitstream, where the first index is used to indicate a first combination, the first combination includes a weight derivation mode and K prediction modes, and K is a positive integer greater than 1; determining a first weight derivation mode and K first prediction modes included in the first combination according to the first index; and obtaining a prediction value of a current block by predicting the current block according to the first weight derivation mode and the K first prediction modes.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Signaling of picture header in video coding

A method of decoding is provided. The method includes receiving a video bitstream including a picture unit (PU), where any decoding capability information (DCI) network abstraction layer (NAL) unit, video parameter set (VPS) NAL unit, sequence parameter set (SPS) NAL unit, or picture parameter set (PPS) NAL unit referred to by the PU precedes a picture header (PH) NAL unit of the PU and a first video coding layer (VCL) NAL unit of the PU; and decoding a coded picture from the PU to obtain a decoded picture.
Owner:HUAWEI TECH CO LTD

Metadata for signaling source picture timing information

Methods, systems, and bitstream syntax are described for video coding and decoding using source picture timing information which is captured by an encoder and is signaled as metadata to a decoder to assist in decoding. The proposed methods include example syntax for signaling source picture timing metadata as supplemental enhancement information (SEI) messaging for both single-layer and multi-layer video sequences.
Owner:DOLBY LABORATORIES LICENSING CORP

Derived intra prediction modes and most probable modes in video coding

A method of encoding or decoding video data comprises: for each respective intra prediction mode of a plurality of intra prediction modes in a most-probable mode (MPM) list: generating, based on reference samples for a template region and using the respective intra prediction mode, prediction samples for the template region; and determining a cost for the respective intra prediction mode; determining a first intra prediction mode and a second intra prediction mode in the MPM list having lowest costs; determining a preliminary prediction block for the first intra prediction mode and a preliminary prediction block for the second intra prediction mode; generating a prediction block based on a fusion of the preliminary prediction blocks weighted according to a weight for the first intra prediction mode and a weight for the second intra prediction mode.
Owner:QUALCOMM INC

E-commerce live broadcast real-time interaction quality evaluation system based on edge calculation

The invention discloses an e-commerce live broadcast real-time interaction quality evaluation system based on edge calculation, and relates to the technical field of e-commerce live broadcast, and the system comprises a multi-modal interaction data collection module which collects multi-modal interaction data of a live broadcast stream in real time through a distributed edge calculation node cluster, and constructs a multi-dimensional quality feature vector, the multi-modal interaction data comprises a video coding parameter, an audio quality index, user interaction behavior data and network transmission state data; according to the invention, the distributed edge computing node cluster collects the multi-modal interaction data of the live stream in real time, the lightweight space-time attention neural network model carries out data fusion processing, the deep reinforcement learning network generates a quality optimization scheme, and the adaptive fuzzy inference system corrects the optimization scheme in real time. And dynamic parameter adjustment is carried out in combination with network bandwidth fluctuation and a terminal device resource state, so that the effect of accurately and comprehensively evaluating the e-commerce live broadcast interaction quality in real time is achieved.
Owner:WUHAN QISHI MEDIA CO LTD

Method and apparatus for video coding using super-resolution in-loop filter

A method and an apparatus for video coding using a super-resolution in-loop filter utilize an in-loop filter based on upsampling or super-resolution techniques in processing a video signal through downsampling to the compression and upsampling to the reconstruction thereof. The video decoding method includes obtaining the reconstructed frame, obtaining a scale value representing a resolution difference between the reconstructed frame and the original frame, generating, based on the scale value, an upsampled reconstructed frame by inputting the reconstructed frame into a resampling in-loop filter that is deep learning-based, and storing an output frame as a reference frame once generated by the plurality of filters and the resampling in-loop filter in a decoded picture buffer (DPB).
Owner:HYUNDAI MOTOR CO LTD +2

Video coding method and system based on multi-channel concurrent software and hardware mixing

The invention relates to the technical field of video coding, in particular to a video coding method and system based on multi-channel concurrent software and hardware mixing, and the method comprises the following steps: analyzing brightness distribution and edge structures, screening effective frames, calculating frame priorities, dividing image blocks and combining processing units, counting the number of frame streams, and analyzing frequency concentration. And evaluating image coherence and a load state, and outputting a processing channel adjustment record. According to the invention, through screening of image content features, occupation of redundant frames on coding resources is reduced, through dynamic configuration of frame priorities, timeliness and accuracy of target frame scheduling are improved, an aggregation strategy of a block structure is combined, picture consistency after image processing is enhanced, and task frequency trend identification is utilized, so that image processing efficiency is improved. According to the method, accurate resource matching of a high-load flow section is achieved, joint judgment of image boundary continuity and structure hopping frequency is adopted, an allocation strategy of a processing channel is optimized, an image structure and channel scheduling form linkage, and stability and adaptive capacity are improved.
Owner:SHENZHEN YOULIAN CLOUD TECH CO LTD

Three-dimensional volume video coding compression method

The invention belongs to the field of volume video coding compression, and particularly relates to a three-dimensional volume video coding compression method, which comprises the following steps of: constructing a voxel space according to sparse point clouds of a three-dimensional volume video and initializing information of each anchor point in the voxel space; determining the three-dimensional position of each neural Gaussian of the anchor point based on the anchor point information; based on the anchor point information and the current visual angle to be rendered, through the mlp of each static attribute, obtaining the static attribute information of each neural Gaussian of the anchor point; based on the anchor point information, the current visual angle to be rendered and the frame to be rendered, the mlp of each dynamic attribute is adopted, and the dynamic attribute information of each neural Gaussian of the anchor point is obtained; obtaining neural Gaussian points in a deformation space through a time projection model based on the dynamic attribute information of the neural Gaussian points in a standard space, thereby obtaining a to-be-rendered view angle and a to-be-rendered frame image; parameters of all mlp and anchor point information of all anchor points are optimized, and finally all anchor point information and all mlp serve as coding compression results. The compression rate can be greatly improved.
Owner:HUAZHONG UNIV OF SCI & TECH

Multi-path embedded video coding method and system based on generative artificial intelligence

The invention provides a multi-path embedded video coding method and system based on generative artificial intelligence. The multi-path embedded video coding method comprises the following steps: firstly, coding input cue words and demand parameters, and outputting cue word vectors and demand parameter code streams; then decoding the cue word vector and the demand parameter code stream, and outputting a feature vector and a feature map; extracting the feature vector, the feature map and the representation guide vector to obtain multi-embedded feature information; reconstructing a picture by using the obtained multi-embedded feature information through a generative AI and obtaining a video to be iterated; performing video quality evaluation on the video to be iterated; and generating a binary code stream for transmission through the current cue word vector, the demand parameter code stream and the multi-embedded feature information input. According to the method, important information characteristics are transmitted in a highly abstracted manner, and a high-definition video is reconstructed at a receiving end, so that the storage space required by video coding and the size of a transmission information stream are greatly reduced, and higher-definition transmission under a narrower bandwidth is realized or video coding under an extremely low bandwidth becomes possible.
Owner:INST OF ADVANCED TECH UNIV OF SCI & TECH OF CHINA +2

Method and apparatus for video coding using an in-loop filter based on a transformer

A method and an apparatus are disclosed for video using an in-loop filter based on Transformer. The video coding method and the apparatus apply a current video block to an attention module of a Transformer, which is a deep learning model. The video coding method and the apparatus utilize the resultant Transformer-based in-loop filter.
Owner:HYUNDAI MOTOR CO LTD +2

Systems and methods for multimodal indexing of video using machine learning

Systems, methods, and computer-readable media are disclosed for systems and methods multimodal indexing of video using machine learning. An example method may include deceiving, by a video encoder of an audio-video transformer neural network comprising one or more computer processors coupled to memory, a first frame and a second frame associated with a first segment of a video. The example method may also include receiving, by an audio encoder of the audio-video transformer neural network, an audio spectrogram comprising first audio data associated with the first segment of the video. generating, by the video encoder, a first video embedding. The example method may also include generating, by the audio encoder, a first audio embedding. The example method may also include determining a fusion of the first video embedding and the first audio embedding using a multimodal bottleneck token. The example method may also include determining an output including the first video embedding and the first audio embedding. The example method may also include determining a classification of the first portion of the video based on the output.
Owner:AMAZON TECH INC

Voice-driven digital human video generation method and device

The embodiment of the invention discloses a method and a device for generating a voice-driven digital human video, which are used for improving the generation quality of the voice-driven digital human video. The method comprises the following steps: acquiring driving voice and a figure reference image; the driving voice and the figure reference image are input into a digital human video generation model, continuous video frames are obtained, and the digital human video generation model is obtained through training of a training sample constructed based on the figure reference image and audio of a figure video and a training label constructed based on the continuous video frames of the figure video; and performing audio and video coding on the driving voice and the continuous video frames to obtain a digital human video.
Owner:HANGZHOU EZVIZ SOFTWARE CO LTD

Nonlinear Peri-Codec Optimization For Image And Video Coding

Nonlinear peri-codec optimization for image and video coding includes obtaining a source image including pixel values expressed in a first defined image sample space, generating a neuralized image representing the source image, the neuralized image including pixel values that are expressed as neural latent space values, encoding the input image wherein the neural latent space values are used as pixel values in a second defined image sample space and the input image is in an operative image format of the encoder, such that a decoder decodes the encoded image to obtain a reconstructed image in the second defined image sample space, wherein the reconstructed image is a reconstructed neuralized image including reconstructed neural latent space values, such that a deneuralized reconstructed image corresponding to the source image is obtained by a nonlinear post-codec image processor in the first defined image sample space.
Owner:GOOGLE LLC

Gesture action video generation method and device based on fine-grained semantic description

The invention discloses a gesture action video generation method and device based on fine-grained semantic description, and the method comprises the steps: carrying out the preprocessing and data enhancement of an original video, and constructing sample data composed of a video frame and a fine-grained semantic description text used for describing a gesture action in the video frame; constructing a training architecture consisting of a video coding module, a text coding module, a noise reduction generation module and a video decoding module; a loss function is constructed based on the difference between added noise in the video coding module and de-noised noise in the de-noising generation module, only parameters of the de-noising generation module are optimized by using the loss function, and a video generation model is formed by the text coding module, the de-noising generation module and the video decoding module after the parameters are optimized; and generating a gesture action video based on the input random vector and the fine-grained semantic description text for describing the gesture action by utilizing a video generation model. In this way, a high-quality general digital human video containing gesture actions is generated based on the fine-grained semantic description text.
Owner:ZHEJIANG UNIV

Adaptive data transmission rate adjusting method and device

The invention relates to the technical field of computers, and discloses a self-adaptive data transmission rate adjustment method, which comprises the following steps: when a multi-person video conference is carried out, acquiring current network condition data corresponding to each participant, and determining a corresponding rate adjustment priority based on audio and video coding parameters in all the current network condition data; calling corresponding historical conference performance data and a pre-trained identification model, and inputting the current network condition data and the historical conference performance data into the identification model to obtain a corresponding identification result; and determining a corresponding target participant based on the identification result and the rate adjustment priority, calling target network state data corresponding to the target participant, and adjusting the audio and video transmission speed of the target participant based on the target network state data. According to the invention, network resources in a multi-person conference can be efficiently utilized.
Owner:SHENZHEN CREATIONBEST INTELLIGENT TECH CO LTD

Cross-component prediction for video coding

A method for video decoding is provided. The method includes obtaining, from a video bitstream, a coding unit in a current picture, wherein the coding unit comprises a luma block and at least one chroma block; and in response to a determination that reconstructed luma samples in the luma block are not to be down-sampled: determining one or more cross-component prediction models based on a luma filter, wherein the one or more cross-component prediction models comprise a convolutional cross-component model (CCCM); obtaining, based on the luma filter, at least one reconstructed luma sample in the luma block that corresponds to a chroma sample in the at least one chroma block; and applying at least one of the one or more cross-component prediction models to the at least one reconstructed luma sample to predict the chroma sample.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

Content-aware partitioning of video frames

A portable electronic device includes a video encoder. The video encoder is configured to receive a video frame. Responsive to the video frame including at least one of a salient object or a region of interest, the video encoder is further configured to partition the video frame into one or more tiles based on a location of the at least one of the salient object or the region of interest.
Owner:ADVANCED MICRO DEVICES INC

Local illumination compensation with coded parameters

A video coding system that uses local illumination compensation to code pixel blocks is provided. A video encoder receives samples for an original block of pixels to be encoded as a current block of a current picture of a video. The video encoder applies a linear model to a reference block to generate a prediction block for the current block. The linear model includes a scale parameter and an offset parameter. The video encoder may use the samples of the original block and samples from a reconstructed reference frame to derive the scale parameter and the offset parameter. The video encoder signals the scale parameter and the offset parameter in a bitstream. The video encoder encodes the current block by using the prediction block to reconstruct the current block.
Owner:MEDIATEK SINGAPORE PTE LTD

MVPS video coding method and device based on deep learning, and medium

The invention discloses an MVPS video coding method and device based on deep learning, and a medium, and relates to the technical field of video coding. The method comprises the following steps: acquiring a video stream, performing time domain and space domain feature extraction on the video stream through a feature extraction unit, and generating a joint feature map through an adaptive weight fusion layer; carrying out bidirectional feature interaction between hierarchies on the combined feature map to obtain a multi-scale feature set; generating a frame-level quantization parameter initial value according to the multi-scale feature set in combination with current network bandwidth feedback; performing time sequence consistency correction on the quantization parameter initial value to generate a target quantization parameter; and performing block coding on the current frame according to the target quantization parameter to generate a coded data stream. According to the method, through dynamic parameter adjustment, hardware algorithm collaborative optimization, cross-frame consistency enhancement and network awareness, the problems of low efficiency, insufficient real-time performance, unstable quality and poor adaptability of a traditional scheme are solved.
Owner:BEIJING TOPMOO TECH

Method and Apparatus for Cross Component Linear Model with Multiple Hypotheses Intra Modes in Video Coding System

A method and apparatus for inter prediction in video coding system are disclosed. According to the method, input data associated with a current block comprising at least one colour block are received. A blending predictor is determined according to a weighted sum of at least two candidate predictions generated based on one or more first hypotheses of prediction, one or more second hypotheses of prediction, or both. The first hypotheses of prediction are generated based on one or more intra prediction modes comprising a DC mode, a planar mode or at least one angular modes. The second hypotheses of prediction are generated based on one or more cross-component modes and a collocated block of said at least one colour block. The input data associated with the colour block is encoded or decoded using the blending predictor.
Owner:MEDIATEK INC

Multiple prediction models and signaling in video coding

A method of encoding or decoding video data includes for each of a plurality of models, deriving respective model parameters associated with respective corresponding models of the plurality of models utilizing a first set of samples; determining a respective cost value associated with the corresponding models of the plurality of models utilizing the respective model parameters and a second set of samples to generate respective cost values for the plurality of models, wherein the first set of samples and the second set of samples are exclusive of one another; determining a model of the plurality of models to use for encoding or decoding a current block based on the respective cost values; and encoding or decoding the current block based on the determined model.
Owner:QUALCOMM INC

Motion compensation considering out-of-boundary conditions in video coding

Methods, apparatuses, and non-transitory computer-readable storage media are provided for video coding. In one method, a decoder derives a first and a second reference pictures for a current coding block; the decoder derives a first and a second predictor samples based on a motion vector associated with the first reference picture using a motion compensation process from the first reference picture; the decoder determines whether the first and the second predictor samples are out-of-boundary (OOB), and in response to determining the first or the second predictor sample is OOB, the decoder replaces the first or the second predictor sample that is OOB with a first or a second alternative predictor sample; and the decoder generates the final prediction sample by averaging sample values of the first predictor sample and the second predictor sample.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

An apparatus, a method and a computer program for video coding and decoding

A method comprising: obtaining an image block unit comprising samples in color channels of one or two chrominance channels and one luminance channel: reconstructing samples of said luminance channel of the image block unit: determining parameters for at least one prediction model for predicting samples of at least one color channel of the image block unit using a prediction model based on one or more reference samples in a neighboring block in current channel / frame, one or more reference samples in a block neighboring a co-located block in a reference channel / frame; and one or more reference samples inside the co-located block in the reference channel / frame; and determining said at least one prediction model as a polynomial and / or exponential prediction model.
Owner:NOKIA TECHNOLOGIES OY

Method and Apparatus of Cross-Component Linear Model Prediction in Video Coding System

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.
Owner:MEDIATEK INC

Quantization offsets for dependent quantization in video coding

A method of processing video data includes determining a quantization level for a coefficient of a current block from a plurality of quantization levels; determining an offset value based on the quantization level, wherein the offset value is a first offset value based on the quantization level being a first quantization level or a second, different offset value based on the quantization level being a second quantization level; determining a quantization parameter or an inverse-quantization parameter for the coefficient based on the determined offset value; and as part of encoding or decoding the current block, performing one of quantization or inverse-quantization for the coefficient based on the determined quantization parameter or the determined inverse-quantization parameter.
Owner:QUALCOMM INC

Methods and devices for multi-hypothesis-based prediction

Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video coding. In one method, a decoder obtains, for a current chroma block, a non-linear model (non-LM) mode and a linear model (LM) mode, and the LM mode includes a cross component linear model (CCLM) mode and a multi-model linear model (MMLM) mode. The decoder then combines the non-LM mode and the LM mode for a multi-hypothesis-based chroma prediction (MCP) for the current chroma block.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD