Video stream data is selectively scaled so that sections within regions of interest (ROI) maintain high resolution while areas not within the region of interest are down-scaled to reduce bandwidth cost of transmission. A low compression encoder compresses sections of a video frame corresponding to one or more ROI without motion search or prediction mode decision to generate low-compression section data. The video frame is downscaled and a high compression encoder compresses the resulting downscaled video frame with prediction mode decision to generate high-compression frame data.

Video stream data is selectively scaled so that sections within regions of interest (ROI) maintain high resolution while areas not within the region of interest are down-scaled to reduce bandwidth cost of transmission. A low compression encoder compresses sections of a video frame corresponding to one or more ROI without motion search or prediction mode decision to generate low-compression section data. The video frame is downscaled and a high compression encoder compresses the resulting downscaled video frame with prediction mode decision to generate high-compression frame data.

A method for lossy image or video encoding, transmission and decoding, the method comprising the steps of: receiving an input image at a first computer system; encoding the first input training image using a first trained neural network to produce a latent representation; performing a quantization process on the latent representation to produce a quantized latent; entropy encoding the quantized latent using a probability distribution, wherein the probability distribution is defined using a tensor network; transmitting the entropy encoded quantized latent to a second computer system; entropy decoding the entropy encoded quantized latent using the probability distribution to retrieve the quantized latent; and decoding the quantized latent using a second trained neural network to produce an output image, wherein the output image is an approximation of the input training image.

Disclosed are an image encoding and decoding method, image processing device, and computer storage medium. the image coding method includes: when copying coding is performed on a current coding block by using one of the at least two different palette and pixel string copying coding manners, generating a new palette color according to pixels of the current coding block; generating a palette for the current coding block according to the new palette color and a palette color candidate set shared by the at least two different palette and pixel string copying coding manners; and performing palette and pixel string copying coding by using the palette for the current coding block, and generating a video bitstream comprising a copying manner and a copying parameter.

Disclosed are an image encoding and decoding method, image processing device, and computer storage medium. the image coding method includes: when copying coding is performed on a current coding block by using one of the at least two different palette and pixel string copying coding manners, generating a new palette color according to pixels of the current coding block; generating a palette for the current coding block according to the new palette color and a palette color candidate set shared by the at least two different palette and pixel string copying coding manners; and performing palette and pixel string copying coding by using the palette for the current coding block, and generating a video bitstream comprising a copying manner and a copying parameter.

A method for generating at least one encoding rule to encode an image captured by an optical sensor. The method includes at least one step of reading in the image captured by the optical sensor, and a step of generating a frequency distribution of an occurrence of light-signal values at different pixels in the image. The method further includes a step of assigning code words to light-signal values, using the frequency distribution, in order to generate the at least one encoding rule for encoding the image captured by the optical sensor.

An encoding device for utility-driven video compression, includes circuitry configured to accept an input video having a first data volume, identify at least a feature of interest in the input video, generate an output video, wherein the output video contains a second data volume that is less than the first data volume and the output video preserves the at least a feature of interest, and encode a bitstream using the output video.

Aspects of the disclosure provide a method, an apparatus, and non-transitory computer-readable storage medium for video decoding. The apparatus includes processing circuitry that is configured to decode a supplemental enhancement information (SEI) message that indicates independent region output information. The independent region output information indicates an independent region that is independently decodable in a current picture. The processing circuitry determines the independent region in the current picture based on offset information and dimension information of the independent region in the independent region output information. The processing circuitry decodes the determined independent region irrespective of whether the entire current picture is decoded. The processing circuitry outputs the decoded independent region based on a position indicated by the offset information and a size indicated by the dimension information of the independent region.

Techniques are described for efficiently embedding frame masks in a video stream. In some solutions, a computer implemented method includes operations for encoding a frame of video data comprising an array of pixels to generate an encoded video frame and transmitting the encoded video frame. The array of pixels can include foreground pixels and background pixels. The foreground pixels can have respective original luma values which are bounded within a first luma range. In certain examples, encoding the frame of video data can include converting the original luma values of the foreground pixels to updated luma values which are bounded within a second luma range. The second luma range can be shifted and/or compressed from the first luma range.

Computing devices, such as mobile computing devices, have access to one or more image sensors that can capture images and video with multiple subjects. Some of these subjects may vary in priority for various tasks. It may be desired to increase or decrease the compression on each subject in order to more efficiently store the image data. Low-power, fast-response machine learning logic can be configured to allow for the generation of a plurality of inference data. Inference data can be associated with the type, motion and/or priority of the subjects as desired. This inference data can be utilized along with other subject data to generate one or more variable compression regions within the image data. The image data can be subsequently processed to compress different areas of the image based on a desired application. The variably compressed image can reduce file sizes and allow for more efficient storage and processing.