Neural texture decoders can suppress DCT ringing artifacts within latent features

A developer has demonstrated that neural texture decoders can effectively suppress DCT ringing and mosquito artifacts within latent features. By placing a quantized DCT in the training loop via evolution strategies, a roughly 500-weight neural network learns to rotate and warp the latent representation so quantization artifacts fall in low-sensitivity directions. The approach allows a level 0 latent to tolerate aggressive libjpeg Q=5 AC quantization that would be catastrophic in image space.

This is very image codec specific: Normally a DCT-based JPEG style codec has mosquito/ringing noise especially on text. But within a neural texture/image codec that places a quantized DCT in the training loop via ES , the neural net can learn how to suppress these artifacts quite effectively. This is a libjpeg Q=5 AC quantization matrix, applied XUASTC/XUBC7 style on the level 0 latent's spatial values - super low DCT quality. The first image is the full texel resolution IDCT decoded level 0 latent, and the second is the fully decompressed image the output from the ~500 weight neural network, after decoding the 2 latents and local "cell" UV as inputs . The latent textures: A latent can tolerate quantization artifacts that would be catastrophic in image space because joint training can rotate/warp the useful representation so those artifacts lie largely in low-sensitivity directions of a tiny learned decoder.