SOURCE-LINKED INTELLIGENCE

Thread-Efficient Decoding for Neural Texture Compression

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Neural texture compression (NTC) achieves higher compression ratios than BCn formats but suffers from GPU thread divergence, which significantly reduces runtime performance. In this work, we propose a shared decoder MLP architecture -- trained with a gradual decoder freezing schedule -- combined with texture clustering to reduce thread divergence by 25%-52% while preserving rendering quality. We evaluate our method on over 500 textures and multiple real rendering scenes, demonstrating up to 8.48x speedup on the Radeon RX 9070 XT GPU compared to non-shared baselines. Our key contributions inclu

Read original source ↗ Open in workspace

recordType

paper

region

Global