Electronic Arts Inc.
Texture compression using a neural network

Abstract:

A computer-implemented method comprises receiving a texture map, segmenting the texture map into a plurality of pixel regions, and for each of the plurality of pixel regions, inputting a vector representation of the pixel region to a compression parameter neural network. The compression parameter neural network is configured to process the vector representation of the pixel region through one or more layers of the compression parameter neural network and generate an output indicating a compression parameter set for compressing the pixel region. The method further comprises inputting the pixel region and the compression parameter set to a compressor, wherein the compressor is configured to compress the pixel region to a compressed representation of the pixel region in accordance with the compression parameter set. A compressed representation of the texture map is stored to a memory accessible by a graphics processing unit, wherein storing the compressed representation of the texture map comprises storing the compressed representations of each of the pixel regions to said memory. The compressed representation of the texture map is selectively decompressed using the graphics processing unit.