An method for determining a video coding test sequence, an electronic device, and a computer readable storage medium are provided. The method includes: determining a candidate video set including multiple candidate videos corresponding to a target service requirement; classifying the candidate videos by content categories to obtain a target distribution of content categories; clustering the candidate videos by values of a preset coding complexity to obtain multiple video classes; selecting from each of the video classes respectively a target class-representative video such that an actual distribution of content categories is consistent with the target distribution of content categories; and constructing a target video coding test sequence based on the target class-representative videos.

An encoding method according to the present disclosure includes: inputting three-dimensional data including three-dimensional coordinate data to a deep neural network (DNN); encoding the three-dimensional data by the DNN to generate encoded three-dimensional data; and outputting the encoded three-dimensional data.

An encoding method according to the present disclosure includes: inputting three-dimensional data including three-dimensional coordinate data to a deep neural network (DNN); encoding the three-dimensional data by the DNN to generate encoded three-dimensional data; and outputting the encoded three-dimensional data.

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.

In one implementation, a picture is partitioned into multiple blocks, with uniform or different block sizes. Each block is compressed by an auto-encoder, which may comprise a deep neural network and entropy encoder. The compressed block may be reconstructed or decoded with another deep neural network. Quantization may be used in the encoder side, and de-quantization at the decoder side. When the block is encoded, neighboring blocks may be used as causal information. Latent information can also be used as input to a layer at the encoder or decoder. Vertical and horizontal position information can further be used to encode and decode the image block. A secondary network can be applied to the position information before it is used as input to a layer of the neural network at the encoder or decoder. To reduce blocking artifact, the block may be extended before being input to the encoder.

A framework and the associated method, schema and design for processing digital data, whether random or not, through encoding and decoding losslessly and correctly for purposes including the purposes of encryption/decryption or compression/decompression or both. There is no assumption of the digital information to be processed before processing. An universal coder is invented and now pigeonhole meets blackhole.

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 hybrid palette-DPCM coding implementation generates a palette for the most dominant colors in an image block and an index block based on the palette. Additionally, for pixels that are not in the palette, DPCM coding is utilized. By combining palette coding and DPCM coding, the image encoding process is optimized.

An image encoding method that generates and encodes a gram matrix representing an image feature when encoding an image to be encoded includes a feature map generation step of generating a plurality of feature maps from the image to be encoded; a gram matrix generation step of generating a gram matrix through calculations between/among the feature maps; a representative vector determination step of generating a representative vector and a representative coefficient value by singular value decomposition of the gram matrix; and a vector encoding step of encoding the representative coefficient value and the representative vector.

Techniques for coding sets of images with neural networks include transforming a first image of a set of images into coefficients with an encoder neural network, encoding a group of the coefficients as an integer patch index into coding table of table entries each having vectors of coefficients, and storing a collection of patch indices as a first coded image. The encoder neural network may be configured with encoder weights determined by jointly with corresponding decoder weights of a decoder neural network on the set of images.