EPFL researchers have developed a machine learning approach to compressing image data with greater accuracy than learning-free computation methods, with applications for retinal implants and other ...

Nvidia researchers have proposed a neural compression method for material textures that, according to results reported in their preprint, can significantly reduce the texture memory footprint during ...

If you read this site, chances are pretty good that you've probably played around with a neural image upscaler at some point. These programs, like the popular "waifu2x", use a pre-trained neural ...

Graphics cards are often limited by their memory. Nvidia’s new image compression technology could now solve this problem. The use of neural networks is expected to drastically reduce the VRAM ...

Intel TSNC brings neural texture compression with up to 18x reduction, faster decoding, and flexible SDK support for modern GPU workflows.

NVIDIA researchers have proposed a neural compression method for material textures that enables random-access lookups and real-time decompression on GPUs, directly targeting the growing strain that ...