Developer Rich Geldreich's NNTC (Non-Neural Texture Compression) PBR material set compressor now supports CPU encoding in addition to CUDA, with encoding and viewing also tested on Windows ARM. The pr…
A developer has built the NNTC Vulkan sample, a 3000+ line C++ implementation that supports VK_NV_cooperative_vector for decoding. The work means the same inference hardware used by neural network wor…
A developer released neural_texture_es2, a self-contained C++ experiment that encodes an RGB image or up to four PBR material textures as a shared low-resolution latent texture plus a tiny MLP decoder…
A developer behind NNTC, an open-source texture compression project on GitHub, reports that a bilinear/degree-2 polynomial decoder fitted to each PBR material can match or beat MLP-based neural textur…
Developer Rich Geldreich released NNTC (Non-Neural Texture Compression) on GitHub, a PBR texture encoder that represents materials with two latents and decodes them using plain linear operations rathe…
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 evolut…
Developer Rich Geldreich released neural block textures, a GPU texture compression method that replaces the fixed hardware decoder with a small configurable MLP (roughly 250-1200 weights) and PVRTC1-s…
A developer has outlined a plan to embed neural block texture codecs directly into the Khronos KTX2 texture format, using KTX2 global data to store MLP inference weights of roughly 250-500 parameters …
A graphics programmer and Binomial LLC co-owner has published a prior art disclosure for "neural block texturing," a hybrid technique combining compressed GPU textures with neural texturing. The discl…
A developer demonstrated a neural block texturing method that compresses a full PBR material stack — normal, roughness, albedo, and ambient occlusion maps — into a single 320-bit record per 6×6 block.…
A developer released a self-contained C++ testbed on GitHub that compresses RGB textures as a shared low-resolution latent texture plus a tiny MLP decoder, trained entirely with Evolution Strategies r…
A developer built a neural block texture compression system that runs entirely on the GPU using CUDA 13.1, combining per-pixel selectors, per-4×4-block latents, and a tiny 1,767-weight MLP decoder tra…
A developer has built a neural GPU texture block compression system that uses Evolution Strategies to train a small MLP decoder, achieving 5.0 bpp of amortized latent data across a texture stack. The …
A developer released a self-contained C++ experiment that encodes an RGB image as a low-resolution latent texture plus a tiny MLP decoder, training both entirely with Evolution Strategies rather than …
A developer prototyped a toy neural texture compression system trained entirely with Evolution Strategies, avoiding backpropagation and derivatives. The setup pairs a 128×128×8 latent texture with a 1…