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.
@article{arxiv.2604.25129,
title = {8DNA: 8D Neural Asset Light Transport by Distribution Learning},
author = {Liwen Wu and Haolin Lu and Bing Xu and Miloš Hašan and Ravi Ramamoorthi},
journal= {arXiv preprint arXiv:2604.25129},
year = {2026}
}