2026/04/28 by Liwen Wu, H Lu, Haolin Lu +3 · 1 voice
Computer Science · #Artificial neural network #Deep neural networks #Global illumination #Inference #Leverage (statistics) #Rendering (computer graphics) #Training set #Variance (accounting) #cs.CV #cs.GR
paper · pdf · open access · doi:10.1145/3799902.3811094
arxiv published 2026/04/28 · arxiv updated 2026/04/28 · openalex publication_date 2026/07/16 · openalex created_date 2026/07/17 · openalex updated_date 2026/07/22
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.