Aspects of the disclosure provide a method and an apparatus including processing circuitry for video decoding. The processing circuitry decodes coding information for a current block. The coding information indicates that the current block is coded in a string copy mode and the coding information includes a first syntax element indicating a string length of a current string in the current block. A coded value of the first syntax element indicates a number N3 of sample groups. Each sample group has L samples, N3 and L being positive numbers. The string length and a number M1 of samples in the current block are divisible by L. The processing circuitry determines a string vector (SV) and the string length of the current string in the current block based on the coding information. The processing circuitry reconstructs the current string based on the SV and the string length of the current string.

This application disclosed video transmission method and devices. An example method includes obtaining a first video and a second video, where the first video and the second video have same content, and image quality of the first video is lower than image quality of the second video. M first video frames and identifier information of N target frames based on the first video are obtained. Related frames corresponding to the N target frames are obtained from the second video based on the identifier information of the N target frames, where the target frames and the related frames have same identifier information but different image quality. The M first video frames and the N related frames are recorded to obtain a third video, where the third video is transmitted to a receiving device, and a data volume of the third video is less than a data volume of the second video.

This application disclosed video transmission method and devices. An example method includes obtaining a first video and a second video, where the first video and the second video have same content, and image quality of the first video is lower than image quality of the second video. M first video frames and identifier information of N target frames based on the first video are obtained. Related frames corresponding to the N target frames are obtained from the second video based on the identifier information of the N target frames, where the target frames and the related frames have same identifier information but different image quality. The M first video frames and the N related frames are recorded to obtain a third video, where the third video is transmitted to a receiving device, and a data volume of the third video is less than a data volume of the second video.

A method for coding/decoding a large field of view video into a bitstream in an immersive rendering system is disclosed. At least one picture of said large field of view video is represented as a surface, said surface being projected onto at least one 2D picture using a projection function. For at least one current block of said at least one 2D picture, at least one item of information representative of a modification of a 2D spatial neighborhood is determined according to said projection function. A group of neighboring blocks using said at least on item of information representative of a modification is determined and at least one part of encoding/decoding of said current block is performed using said determined group of neighboring blocks.

Neural network based substitutional end-to-end (E2E) image compression (NIC) being performed by at least one processor and includes receiving an input image to an E2E NIC framework, determining a step size of the input image indicating a learning rate of a training model, determining a substitute image based on the training model, encoding the substitute image in lieu of the input image to generate a bitstream, and mapping the substitute image to the bitstream to generate a compressed representation. Further, step size may be determined by a scheduler and change throughout the training of the training model. The image may also be split into patches for which a scheduler is assigned for each patch and each patch is encoded instead of the entire input image.

A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

An artificial intelligence (AI) decoding method including obtaining image data generated from performing first encoding on a first image and AI data related to AI down-scaling of at least one original image related to the first image; obtaining a second image corresponding to the first image by performing first decoding on the image data; obtaining, based on the AI data, deep neural network (DNN) setting information for performing AI up-scaling of the second image; and generating a third image by performing the AI up-scaling on the second image via an up-scaling DNN operating according to the obtained DNN setting information. The DNN setting information is DNN information updated for performing the AI up-scaling of at least one second image via joint training of the up-scaling DNN and a down-scaling DNN used for the AI down-scaling.

A method, computer program, and computer system is provided for coding video data. Video data is received, and an edge present within a sample of the received video data is detected. A gradient value corresponding to a direction associated with the detected edge is calculated. The video data is decoded based on the calculated gradient.

An image encoding/decoding method and apparatus are provided. An image decoding method according to the present disclosure includes: receiving an image, in which a first atlas for a basic view of a current image and a second atlas for an additional view of the current image are merged; extracting an image divided in a predetermined image unit within the first atlas and the second atlas; dividing the first atlas and the second atlas in the predetermined image unit; and reconstructing the image divided in the predetermined image unit, wherein the dividing of the first atlas and the second atlas in the predetermined image unit may non-uniformly divide the first atlas and the second atlas.

It is made possible to reduce motion picture quality degradation caused by strobing in a layer of a basic frame frequency and to maintain a high image quality in layers of the other frame frequencies. Image data in a plurality of frequency layers (only image data regarding a lowermost frequency layer is subjected to blending processing using image data regarding another frequency layer) obtained by hierarchically decomposing image data at a predetermined frame frequency is received. Image data for display is obtained according to a display capability, using image data regarding layers from the lowermost frequency layer up to a predetermined higher frequency layer. It is possible to reduce the motion picture quality degradation caused by the strobing in the layer of the basic frame frequency (frame frequency of the lowermost frequency layer) and to maintain the high image quality in the layers of the other frame frequencies.