NVIDIA Unlocks Higher Quality Textures With Neural Compression For 4X VRAM Savings
Created on 2023-05-08T03:37:48-05:00
Nvidia whitepaper: Random-Access Neural Compression of Material Textures
the paper describes a novel method of compressing game material textures that can store up to 16x more data in the same space as traditional block-based compression methods.
Competitive against AVIF and JPEG-XL, with provisos.
Is heavily dependent on exploiting redundant information across material channels. ex. color and bump information is all merged together and decompressed together, and misalignments in details across the channels can majorly affect compression performance.