Zhejiang University

Huawei Technologies Co., Limited

Guangdong Oppo Mobile Telecommunications Corp., Ltd.

Sz Dji Technology Co., Ltd.

Xi'an Zhongxing New Software Co., Ltd.

Samsung Electronics Co., Ltd.

Zte Corporation

Shanghai Zhongxing Software Company Limited

Urban Planning & Design Institute of Shenzhen

Lu Yu

Yin Zhao

Hualong Yu

Zhenyu Dai

Haitao Yang

Zhihuang Xie

Ming Li

Yingjie Hong

Ye-Kui Wang

Xiaozhen Zheng

Jie Chen

Dong Wang

Yuqun Fan

Pu Li

Yichen Zhang

Xiaoding Gao

Peiyun Di

Feng Li

Mingyuan Yang

Lianhuan Xiong

Xuguang Zuo

Wenyi Wang

Jiafeng Chen

Bingjie Zhu

Sijia Chen

Zhichu He

Xiaojun Li

Xingguo Zhu

Yan Du

Jue Mao

Zhenjiang Shao

Wenhao Hong

Yuchao Shao

Xuchang Huangfu

Nian Ding

Sicheng Li

Yong Ling

Chuchu Wang

Jianpeng Wang

Peng Lv

Yaqing Pan

Xiangyu Lin

Qichao Yuan

Shangwen Li

Binbin Yu

Embodiments of the disclosure provide an encoding method, a decoding method, an encoder, a decoder, and a storage medium. The method includes the following. An encoding result of a current block, a target index for the current block, and a block-coding enable flag for the current block are obtained by parsing a bitstream. A feature map splicing order is obtained. When the block-coding enable flag is valid, target block-coding motion information corresponding to the target index is determined based on the feature map splicing order and pixel position information of the current block. The encoding result of the current block is decoded based on the target block-coding motion information.

Encoding method, decoding method, and decoder

An image processing method, an encoding method, an image processing apparatus, and an encoding apparatus are provided. The image processing method includes the following operations. An encoded bitstream is received from a trained encoder. The encoded bitstream is decoded by a trained decoder to obtain a decoded reconstructed image. The decoded reconstructed image or the decoded reconstructed image subjected to image post-processing is processed by a trained task execution network to perform or complete a machine learning task. The trained encoder and the trained decoder belong to a trained codec network.

Image processing, network training and encoding methods, apparatus, device, and storage medium

A decoding method, a decoder, and an encoder are provided. A view synthesis technology is used to obtain, according to a reference view image, a synthesized image of a view to be encoded, comprising a texture image and a depth image, and a hole filling technology is used to predict hole area information and perform hole filling on the synthesized image of said view to obtain a predicted image.

Decoding method, inter-view prediction method, decoder, and encoder

An encoding method, a decoding method, an encoder, a decoder, and a storage medium are provided. The encoding method comprises: determining input feature map data (S); performing relevant processing on the input feature map data to obtain a plurality of feature sub-maps (S); reordering the plurality of feature sub-maps to obtain a quasi time domain sequence and corresponding reordering information (S); and encoding the quasi time domain sequence and the reordering information to generate a bitstream ().

Encoding and decoding methods using input feature map processing for quasi time domain sequence

A data encoding method includes obtaining an attribute residual of a current point cloud point, binarizing the attribute residual to obtain a binary code of the current point cloud point that includes a first binary code indicating a first flag bit and a second binary code indicating a second flag bit, selecting a first context model from a context model list according to a first condition, selecting a second context model from the context model list according to a second condition, encoding the first binary code using the first context model, and encoding the second binary code using the second context model. The first condition and the second condition are different for the first context model and the second context model corresponding to a same index in the context model list.

Method, device, and storage medium for data encoding/decoding

A feature data encoding method is provided. First feature data corresponding to each of channels to be encoded is determined; data type conversion processing is performed on the first feature data corresponding to each channel to obtain second feature data that meets a data input condition of an apparatus for encoding feature data; spatial re-expression is performed on the second feature data corresponding to each channel to obtain third feature data, wherein a height of the third feature data is a first height, a width of the third feature data is a first width, and the third feature data comprises the second feature data located at a target position of each of the channels; and the third feature data is encoded and signalled in a bitstream.

Feature data encoding method, apparatus and device, feature data decoding method, apparatus and device, and storage medium

A data encoding method includes determining a value of a syntax element of point cloud data of a point cloud. The point cloud data includes attribute values of the point cloud and the syntax element indicates a search range of the attribute values during prediction encoding. The method further includes performing prediction processing on the attribute values according to the search range to obtain residuals of the attribute values, and encoding the residuals and a difference between the value of the syntax element and a constant value to generate code stream data. The constant value is a positive number.

A method for processing a video data stream, a video decoding apparatus, and a method for encoding data stream are provided. The method includes: receiving a video data stream; generating a layer list using at least the patch-layer association information, the layer list including a first layer associated with the first view, the first layer being based on a first depth of the first view; assigning a first layer identification to the first layer; updating the view list section by adding the first layer as a second view; selecting a first target view for rendering on an output device; selecting one or more patches using at least the layer list and the patch list section; combining the selected one or more patches to form a first intermediate output frame; and performing post processing using at least the view list section.

Method for processing video data stream, video decoding apparatus, and method for encoding data stream

Methods to produce media data ensure a method for media data transmitting, and a method for media data processing, and the synchronization and correct processing and transmission of bitstreams on the basis of dependency relation between video layer bitstream and library layer bitstream, and correct bitstream is highly efficiently provided to a decoder. With methods for reference picture request processing and reference picture specifying, a current picture includes a library picture set in which the library picture does not belong to the random access segment to which the current picture belongs and the previously most adjacent random access segment, and correct decoding of the current picture is ensured and repeated downloading of library pictures is avoided, thus ensuring the correct decoding and highly efficient transmission of a bitstream produced by library-based video coding method, and increasing transmission efficiency and storage efficiency.

Methods and apparatus for media data processing and transmitting and reference picture specifying

A picture encoding/decoding method and a related apparatus are provided. The picture decoding method includes obtaining a current picture from a video, the current picture being segmented using random access points into multiple video segments supporting a random access function; selecting, from a knowledge base, K reference pictures of the current picture, wherein at least one reference picture in the knowledge base does not belong to a random access segment in which the current picture is located, the random access segment comprising a picture sequence arranged in a decoding order from a closest random access point before the current picture to a closest random access point after the current picture; and decoding the current picture according to the K reference pictures.

Picture encoding/decoding method and related apparatus

A method of bitstream verifying includes at the encoder side, the coded picture data of a spliced bitstream, containing a library bitstream and a main bitstream, is processed by different operations in the hypothetical bitstream buffer to simulate the data fulfillment level of the bitstream buffer. This is used to check whether the hypothetical bitstream buffer is overflowed or underflowed and verify the qualification of the bitstream. A method of managing bitstream at the decoder side is exploited to decode the library picture, which is inserted in the spliced bitstream, at a proper time. This ensures that a bitstream buffer with a limited capacity neither overflows nor underflows and the decoder can decode and present the picture of the main bitstream at a proper temporal order, which avoids lag of the main bitstream picture and waste of the decoded picture buffer.

Methods and apparatus of bitstream verifying and decoding

Disclosed are multiple methods and multiple apparatus e media data, and multiple methods and multiple apparatus for media data transmitting, media data processing, reference picture request processing and reference picture specifying. By means of the method to produce media data, the method for media data transmitting, and the method for media data processing, the synchronization and correct processing and transmission of bitstreams are ensured on the basis of dependency relation between video layer bitstream and library layer bitstream, and correct bitstream is highly efficiently provided to a decoder. By means of the method for reference picture request processing and reference picture specifying, a current picture is provided with a library picture set in which the library picture does not belong to the random access segment to which the current picture belongs and the previously most adjacent random access segment, and correct decoding of the current picture is ensured and repeated downloading of library pictures is avoided, thus ensuring the correct decoding and highly efficient transmission of a bitstream produced by library-based video coding method, and increasing transmission efficiency and storage efficiency.

A video encoding method, a video decoding method, an apparatus, a device, and a storage medium include parsing a first flag from the video bitstream when a video bitstream is allowed to be decoded by referencing a library picture corresponding to a library picture bitstream, using a value of a target parameter of the video bitstream as a value of a target parameter of the library picture bitstream referenced by the video bitstream when a value of the first flag is a first value, and reconstructing, based on the value of the target parameter of the library picture bitstream referenced by the video bitstream and the library picture bitstream referenced by the video bitstream to obtain the library picture corresponding to the library picture bitstream referenced by the video bitstream.

Video coding and decoding methods and devices using a library picture bitstream

The invention provides an information preserving coding method based on possibility distribution of value of a sample. The possibility distribution of value of a sample refers to evaluation of the possibility of various values of the sample. The information preserving coding method provided is more in line with the non-stationary probability property of an actual source, and a coding code length is the overhead caused by a prediction error of the possibility distribution of value of the sample. The invention further provides multiple coding methods based on possibility distribution of value of a sample. Through improving the prediction accuracy of the possibility distribution of value of the sample, the coding efficiency is greatly improved.

Information preserving coding and decoding method and device

A decoding method includes obtaining an identifier from a bitstream, where the identifier indicates a minimum decoding time interval k between library pictures that is allowed in the bitstream, obtaining, when parsing the bitstream, a decoding moment tof a current decoded picture and a decoding moment tof a first decoded picture that is closest to the current decoded picture and that references a new library picture when the current decoded picture is decoded by referencing a library picture, where the new library picture is a library picture that is not decoded or needs to be re-decoded when the first decoded picture is decoded, and determining a preset quantity of library pictures as candidate reference pictures of the current decoded picture based on a relationship between k and a difference between tand t.

Video encoder, video decoder, and corresponding method of predicting random access pictures

Growing community of inventors

Hangzhou, China

Lu Yu