通过共享解码器与聚类，显著提升神经纹理压缩的运行效率。
Thread-Efficient Decoding for Neural Texture Compression
- 采用共享解码器架构与渐进冻结训练，减少线程发散。
- 在500+纹理上实现最高8.48倍加速，质量无损失。
- 适合游戏/渲染领域追求高性能的开发者使用。
神经纹理压缩（NTC）虽可实现比传统编码格式更高的压缩率，但因GPU线程发散导致运行效率低下。本文提出一种共享解码器MLP架构，结合渐进式解码器冻结训练策略与基于CLIP嵌入的语义聚类方法，将线程发散降低25%-52%，同时保持渲染质量。我们在超过500个纹理及多个真实渲染场景上评估该方法，相比非共享基线，在Radeon RX 9070 XT GPU上实现最高8.48倍加速。主要贡献包括：(1) 统一的共享解码器架构，通过纹理分组减少发散；(2) 渐进冻结训练方案，提升稳定性与重建精度；(3) 基于CLIP的语义聚类策略，实现高效解码器共享；(4) 全面的性能与消融实验验证方法有效性。
原文摘要 · Abstract (English)
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 include: (1) a unified shared decoder architecture that reduces divergence by grouping textures; (2) a training recipe with gradual decoder freezing that improves stability and reconstruction accuracy; (3) a semantic clustering strategy using CLIP embeddings that groups similar textures for effective decoder sharing; and (4) comprehensive performance and ablation studies validating our approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。