8DNA用神经网络预烘焙8维光照传输，实现近场光照下高保真渲染。
8DNA: 8D Neural Asset Light Transport by Distribution Learning
- 通过分布学习从路径追踪样本中训练8维光照模型
- 在复杂资产上实现接近路径追踪的渲染效果，且方差更低
- 适合需要快速高精度渲染的3D内容创作场景
高保真3D资产常包含次表面散射、光泽互反射和细粒度纤维散射等全局光照效应，这些效应涉及长程散射路径，模拟成本高昂。本文提出8D神经资产（8DNA），将这些光照传输效应预先烘焙至神经表示中。与以往假设远场光照并预计算6维函数的方法不同，8DNA学习完整的8维光照传输，支持近场光照下的精确渲染。训练采用分布学习框架，从正向路径追踪样本中学习光照传输，相比传统回归方法，在更小训练预算下仍能降低优化方差。实验表明，8DNA在多种场景配置下渲染结果接近路径追踪，同时在挑战性资产上实现更低方差和更快推理速度。
原文摘要 · Abstract (English)
High-fidelity 3D assets exhibit intriguing global illumination effects like subsurface scattering, glossy interreflections, and fine-scale fiber scatterings, which often involve long scattering paths that are expensive to simulate. We introduce 8D neural assets (8DNA) to pre-bake these light transport effects into neural representations. Unlike prior methods that assume far-field lighting and precompute light transport into 6D functions, 8DNA learns the full 8D light transport, enabling accurate rendering under near-field illumination. Our training leverages a distribution-learning formulation that learns light transport from forward path-traced samples, which produces less optimization variance with lower training budget than the prior regression-based approaches. Experiments show our 8DNA rendering closely matches path-traced results under various scene configurations, yet it achieves improved variance reduction and fast inference speeds on challenging assets.
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。