An encoding device evaluates a plurality of processing and/or post-processing algorithms and/or methods to be applied to a video stream, and signals a selected method, algorithm, class or category of methods/algorithms either in an encoded bitstream or as side information related to the encoded bitstream. A decoding device or post-processor utilizes the signaled algorithm or selects an algorithm/method based on the signaled method or algorithm. The selection is based, for example, on availability of the algorithm/method at the decoder/post-processor and/or cost of implementation. The video stream may comprise, for example, downsampled multiplexed stereoscopic images and the selected algorithm may include any of upconversion and/or error correction techniques that contribute to a restoration of the downsampled images.

A computer-implemented method comprises receiving a first compressed representation of a texture map in a first compression format, wherein the first compressed representation has been compressed using a first compressor, and receiving an array of compression parameters for a second compressor, the array of compression parameters including one or more respective compression parameters for each of a plurality of pixel regions of the texture map. The method further comprises decompressing the first compressed representation of the texture map to obtain the texture map, and compressing, using the second compressor, the texture map to a second compressed representation in a second compression format, comprising compressing each of said plurality of pixel regions of the texture map in accordance with the respective one or more compression parameters. The method further comprises storing the second compressed representation of the texture map to one or more memories accessible by a graphics processing unit, and selectively decompressing portions of the second compressed representation of the texture map using the graphical processing unit.

A method of decoding video data includes determining that a geometric partition mode is enabled for a current block of the video data and determining a split line dividing the current block into a first partition and a second partition, where determining the split line comprises selecting an angle for the split line from a plurality of angles, Each angle of the plurality of angles corresponding to an N:M ratio of samples of the current block, where N and M are integers. The split line is not at a corner of the current block. The method further includes determining geometric mode weights for the current block using the angle of the split line, generating a first prediction block using motion information for the first partition, and generating a second prediction block using motion information for the second partition.

A video processing method is provided. A target video frame is obtained from a video. A target data block is determined from the target video frame. Data block indicator information of the target data block is determined based on a scene complexity of the target data block. The target data block is divided into a plurality of subdata blocks. Subblock indicator information of the subdata blocks are determined based on scene complexities of the subdata blocks. An encoding mode for the target data block is determined according to the data block indicator information and the subblock indicator information. The target data block is encoded according to the determined encoding mode.

A video processing method is provided. A target video frame is obtained from a video. A target data block is determined from the target video frame. Data block indicator information of the target data block is determined based on a scene complexity of the target data block. The target data block is divided into a plurality of subdata blocks. Subblock indicator information of the subdata blocks are determined based on scene complexities of the subdata blocks. An encoding mode for the target data block is determined according to the data block indicator information and the subblock indicator information. The target data block is encoded according to the determined encoding mode.

A system for non-reference video-quality prediction includes a video-processing block to receive an input bitstream and to generate a first vector, and a neural network to provide a predicted-quality vector after being trained using training data. The training data includes the first vector and a second vector, and elements of the first vector include high-level features extracted from a high-level syntax processing of the input bitstream.

A system for non-reference video-quality prediction includes a video-processing block to receive an input bitstream and to generate a first vector, and a neural network to provide a predicted-quality vector after being trained using training data. The training data includes the first vector and a second vector, and elements of the first vector include high-level features extracted from a high-level syntax processing of the input bitstream.

A device includes a memory and one or more processors. The memory is configured to store an image enhancement network of an image enhancer. The one or more processors are configured to predict an image compression quality of an image of a stream of images. The one or more processors are also configured to configure the image enhancer based on the image compression quality. The one or more processors are further configured to process, using the image enhancement network of the configured image enhancer, the image to generate an enhanced image.

A device includes a memory and one or more processors. The memory is configured to store an image enhancement network of an image enhancer. The one or more processors are configured to predict an image compression quality of an image of a stream of images. The one or more processors are also configured to configure the image enhancer based on the image compression quality. The one or more processors are further configured to process, using the image enhancement network of the configured image enhancer, the image to generate an enhanced image.

This disclosure describes systems, methods, and devices related to complexity aware encoding. A device may generate a list of encodes based on pairs of resolution and quantization parameters (QP) pairs associated with one or more video segments received from a source. The device may generate an estimated bit rate associated with the one or more video segments based on an analysis of the one or more video segments. The device may determine distortion values associated with the one or more video segments. The device may apply a weighting mechanism to the distortion values using the estimated bit rate. The device may select a subset of encodes based on the weighting mechanism. The device may perform the subset of encodes on the one or more video segments for transmission.