In various embodiments, a training application trains a machine learning model to preprocess images. In operation, the training application computes a chroma sampling factor based on a downscaling factor and a chroma subsampling ratio. The training application executes a machine learning model that is associated with the chroma sampling factor on data that corresponds to both an image and a first chroma component to generate preprocessed data corresponding to the first chroma component. Based on the preprocessed data, the training application updates at least one parameter of the machine learning model to generate a trained machine learning model that is associated with the first chroma component.

In various embodiments, a training application trains a machine learning model to preprocess images. In operation, the training application computes a chroma sampling factor based on a downscaling factor and a chroma subsampling ratio. The training application executes a machine learning model that is associated with the chroma sampling factor on data that corresponds to both an image and a first chroma component to generate preprocessed data corresponding to the first chroma component. Based on the preprocessed data, the training application updates at least one parameter of the machine learning model to generate a trained machine learning model that is associated with the first chroma component.

A method for decoding or encoding includes obtaining views parameters for a set of views comprising at least one reference view and a current view of a multi-views video content wherein each view comprises a texture layer and a depth layer. For at least one couple of a reference view and the current view of the set of views, an intermediate prediction image applying a forward projection method to pixels of the reference view is generated to project these pixels from a camera coordinates system of the reference view to a camera coordinates system of the current view, the prediction image comprising information allowing reconstructing image data. At least one final prediction image obtained from at least one intermediate prediction image is stored in a buffer of reconstructed images of the current view. A current image of the current view from the images stored in said buffer is reconstructed, said buffer comprising said at least one final prediction image.

A method for decoding or encoding includes obtaining views parameters for a set of views comprising at least one reference view and a current view of a multi-views video content wherein each view comprises a texture layer and a depth layer. For at least one couple of a reference view and the current view of the set of views, an intermediate prediction image applying a forward projection method to pixels of the reference view is generated to project these pixels from a camera coordinates system of the reference view to a camera coordinates system of the current view, the prediction image comprising information allowing reconstructing image data. At least one final prediction image obtained from at least one intermediate prediction image is stored in a buffer of reconstructed images of the current view. A current image of the current view from the images stored in said buffer is reconstructed, said buffer comprising said at least one final prediction image.

A method of decoding may comprise: receiving a bitstream comprising compressed video/image data; parsing or deriving, from the bitstream, an output layer set mode indicator in a video parameter set (VPS); identifying output layer set signaling based on the output layer set mode indicator; identifying one or more picture output layers based on the identified output layer set signaling; and decoding the identified one or more picture output layers.

A method of decoding may comprise: receiving a bitstream comprising compressed video/image data; parsing or deriving, from the bitstream, an output layer set mode indicator in a video parameter set (VPS); identifying output layer set signaling based on the output layer set mode indicator; identifying one or more picture output layers based on the identified output layer set signaling; and decoding the identified one or more picture output layers.

Systems and methods for coding and decoding are provided. A method includes: obtaining a coded video stream by coding video data, the coded video stream including a picture partitioned into a plurality of sub-pictures, and further including adaptive resolution change (ARC) information that is signaled directly within a header of a sub-picture from among the plurality of sub-pictures, or that is provided within a parameter set and directly referenced in the header; and outputting the coded video stream, wherein the header is within a network abstraction layer (NAL) unit that has a scope of the sub-picture.

Systems and methods for coding and decoding are provided. A method includes: obtaining a coded video stream by coding video data, the coded video stream including a picture partitioned into a plurality of sub-pictures, and further including adaptive resolution change (ARC) information that is signaled directly within a header of a sub-picture from among the plurality of sub-pictures, or that is provided within a parameter set and directly referenced in the header; and outputting the coded video stream, wherein the header is within a network abstraction layer (NAL) unit that has a scope of the sub-picture.

This disclosure relates to video coding and more particularly to techniques for signaling picture timing and decoding unit information for coded video. According to an aspect of an invention, a flag syntax element, specifying whether decoding unit level decoded picture buffer output delay parameters are present in a picture timing message, in a buffering period message is parsed and a first syntax element, used to compute a decoded picture buffer output time, in the picture timing message is parsed, in a case that a value of the flag syntax element is equal to one.

This application discloses image encoding and decoding methods and apparatuses. The image encoding method includes performing, by a source device, compression encoding on an image to obtain base layer information. The method further includes obtaining enhancement layer information based on the base layer information and the image. The method further includes obtaining control layer information. The method further includes performing encoding and modulation on the control layer information, the base layer information, and the enhancement layer information separately to obtain a plurality of symbol sets. The method further includes mapping the plurality of symbol sets to a resource for sending. Embodiments of this application may ensure robustness in a transmission process and improve overall compression efficiency and performance.