Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.

A method for lossily compressing a sequence of video frames into a representation, wherein each video frame comprises pixels that carry color values. The method includes: segmenting each video frame into superpixels, wherein these superpixels are groups of pixels that share at least one predetermined common property; assigning, to each superpixel in each video frame, at least one attribute derived from the pixels belonging to the respective superpixel; and combining superpixels as nodes in a graph representation, wherein superpixels in a same video frame are connected by spatial edges associated with at least one quantity that is a measure for a distance between these superpixels; and in response to superpixels in adjacent video frames in the sequence meeting at least one predetermined relatedness criterion, these superpixels are connected by temporal edges.

A method for lossily compressing a sequence of video frames into a representation, wherein each video frame comprises pixels that carry color values. The method includes: segmenting each video frame into superpixels, wherein these superpixels are groups of pixels that share at least one predetermined common property; assigning, to each superpixel in each video frame, at least one attribute derived from the pixels belonging to the respective superpixel; and combining superpixels as nodes in a graph representation, wherein superpixels in a same video frame are connected by spatial edges associated with at least one quantity that is a measure for a distance between these superpixels; and in response to superpixels in adjacent video frames in the sequence meeting at least one predetermined relatedness criterion, these superpixels are connected by temporal edges.

A video decoding method includes determining, based on an area of a current block, whether a multi-prediction combination mode for predicting the current block by combining prediction results obtained according to a plurality of prediction modes is applied to the current block, when the multi-prediction combination mode is applied to the current block, determining the plurality of prediction modes to be applied to the current block, generating a plurality of prediction blocks of the current block, according to the plurality of prediction modes, and determining a combined prediction block of the current block, by combining the plurality of prediction blocks according to respective weights.

In communication applications, aggregate source image data at a transmitter exceeds the data that is needed to display a rendering of a viewport at a receiver. Improved streaming techniques that include estimating a location of a viewport at a future time. According to such techniques, the viewport may represent a portion of an image from a multi-directional video to be displayed at the future time, and tile(s) of the image may be identified in which the viewport is estimated to be located. In these techniques, the image data of tile(s) in which the viewport is estimated to be located may be requested at a first service tier, and the other tile in which the viewport is not estimated to be located may be requested at a second service tier, lower than the first service tier.

In communication applications, aggregate source image data at a transmitter exceeds the data that is needed to display a rendering of a viewport at a receiver. Improved streaming techniques that include estimating a location of a viewport at a future time. According to such techniques, the viewport may represent a portion of an image from a multi-directional video to be displayed at the future time, and tile(s) of the image may be identified in which the viewport is estimated to be located. In these techniques, the image data of tile(s) in which the viewport is estimated to be located may be requested at a first service tier, and the other tile in which the viewport is not estimated to be located may be requested at a second service tier, lower than the first service tier.

A video transmission method according to embodiments may comprise the steps of: encoding video data; and transmitting the video data. A video reception method according to embodiments may comprise the steps of: receiving video data; and decoding the video data.

Systems and methods are disclosed for image signal processing. For example, methods may include receiving a current image of a sequence of images from an image sensor; combining the current image with a recirculated image to obtain a noise reduced image, where the recirculated image is based on one or more previous images of the sequence of images from the image sensor; determining a noise map for the noise reduced image, where the noise map is determined based on estimates of noise levels for pixels in the current image, a noise map for the recirculated image, and a set of mixing weights; recirculating the noise map with the noise reduced image to combine the noise reduced image with a next image of the sequence of images from the image sensor; and storing, displaying, or transmitting an output image that is based on the noise reduced image.

Systems and methods are disclosed for image signal processing. For example, methods may include receiving a current image of a sequence of images from an image sensor; combining the current image with a recirculated image to obtain a noise reduced image, where the recirculated image is based on one or more previous images of the sequence of images from the image sensor; determining a noise map for the noise reduced image, where the noise map is determined based on estimates of noise levels for pixels in the current image, a noise map for the recirculated image, and a set of mixing weights; recirculating the noise map with the noise reduced image to combine the noise reduced image with a next image of the sequence of images from the image sensor; and storing, displaying, or transmitting an output image that is based on the noise reduced image.

A method includes obtaining an embedded sparse image data for generating a target image data from an image signal processor, wherein the embedded sparse image data includes a sparse image data including pixels which include at least first color pixels, second color pixels and third color pixels; extracting a split data including first and second data parts from the sparse image data; joining the first and second data parts to obtain a compressed data; inversely converting the compressed data based on a compression curve to obtain an inversely converted residual data; adding a random value within an error range to the inversely converted residual data to obtain a reconstructed residual data; and reconstructing a dense image data based on the reconstructed residual data and the sparse image data, wherein the dense image data includes pixels including the first color pixels.