Random-Access Neural Compression of Material Textures
This addresses storage and memory issues for real-time rendering applications, offering a domain-specific incremental improvement.
The authors tackled the problem of growing storage and memory demands for material textures in rendering by proposing a neural compression technique that unlocks 16x more texels with better image quality than AVIF and JPEG XL, while enabling real-time random-access decompression on GPUs.
The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed for material textures. We unlock two more levels of detail, i.e., 16x more texels, using low bitrate compression, with image quality that is better than advanced image compression techniques, such as AVIF and JPEG XL. At the same time, our method allows on-demand, real-time decompression with random access similar to block texture compression on GPUs, enabling compression on disk and memory. The key idea behind our approach is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them. Finally, we use a custom training implementation to achieve practical compression speeds, whose performance surpasses that of general frameworks, like PyTorch, by an order of magnitude.