Neural Inverse Rendering from Propagating Light

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Malik, Anagh, Attal, Benjamin, Xie, Andrew, O'Toole, Matthew, Lindell, David B.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912415800623104
author Malik, Anagh
Attal, Benjamin
Xie, Andrew
O'Toole, Matthew
Lindell, David B.
author_facet Malik, Anagh
Attal, Benjamin
Xie, Andrew
O'Toole, Matthew
Lindell, David B.
contents We present the first system for physically based, neural inverse rendering from multi-viewpoint videos of propagating light. Our approach relies on a time-resolved extension of neural radiance caching -- a technique that accelerates inverse rendering by storing infinite-bounce radiance arriving at any point from any direction. The resulting model accurately accounts for direct and indirect light transport effects and, when applied to captured measurements from a flash lidar system, enables state-of-the-art 3D reconstruction in the presence of strong indirect light. Further, we demonstrate view synthesis of propagating light, automatic decomposition of captured measurements into direct and indirect components, as well as novel capabilities such as multi-view time-resolved relighting of captured scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05347
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Inverse Rendering from Propagating Light
Malik, Anagh
Attal, Benjamin
Xie, Andrew
O'Toole, Matthew
Lindell, David B.
Computer Vision and Pattern Recognition
We present the first system for physically based, neural inverse rendering from multi-viewpoint videos of propagating light. Our approach relies on a time-resolved extension of neural radiance caching -- a technique that accelerates inverse rendering by storing infinite-bounce radiance arriving at any point from any direction. The resulting model accurately accounts for direct and indirect light transport effects and, when applied to captured measurements from a flash lidar system, enables state-of-the-art 3D reconstruction in the presence of strong indirect light. Further, we demonstrate view synthesis of propagating light, automatic decomposition of captured measurements into direct and indirect components, as well as novel capabilities such as multi-view time-resolved relighting of captured scenes.
title Neural Inverse Rendering from Propagating Light
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.05347