8DNA: 8D Neural Asset Light Transport by Distribution Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911627959336960 |
|---|---|
| author | Wu, Liwen Lu, Haolin Xu, Bing Hašan, Miloš Ramamoorthi, Ravi |
| author_facet | Wu, Liwen Lu, Haolin Xu, Bing Hašan, Miloš Ramamoorthi, Ravi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25129 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 8DNA: 8D Neural Asset Light Transport by Distribution Learning Wu, Liwen Lu, Haolin Xu, Bing Hašan, Miloš Ramamoorthi, Ravi Graphics Computer Vision and Pattern Recognition 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. |
| title | 8DNA: 8D Neural Asset Light Transport by Distribution Learning |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.25129 |