ROGR: Relightable 3D Objects using Generative Relighting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tang, Jiapeng, Levine, Matthew, Verbin, Dor, Garbin, Stephan J., Nießner, Matthias, Brualla, Ricardo Martin, Srinivasan, Pratul P., Henzler, Philipp
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917123515744256
author Tang, Jiapeng
Levine, Matthew
Verbin, Dor
Garbin, Stephan J.
Nießner, Matthias
Brualla, Ricardo Martin
Srinivasan, Pratul P.
Henzler, Philipp
author_facet Tang, Jiapeng
Levine, Matthew
Verbin, Dor
Garbin, Stephan J.
Nießner, Matthias
Brualla, Ricardo Martin
Srinivasan, Pratul P.
Henzler, Philipp
contents We introduce ROGR, a novel approach that reconstructs a relightable 3D model of an object captured from multiple views, driven by a generative relighting model that simulates the effects of placing the object under novel environment illuminations. Our method samples the appearance of the object under multiple lighting environments, creating a dataset that is used to train a lighting-conditioned Neural Radiance Field (NeRF) that outputs the object's appearance under any input environmental lighting. The lighting-conditioned NeRF uses a novel dual-branch architecture to encode the general lighting effects and specularities separately. The optimized lighting-conditioned NeRF enables efficient feed-forward relighting under arbitrary environment maps without requiring per-illumination optimization or light transport simulation. We evaluate our approach on the established TensoIR and Stanford-ORB datasets, where it improves upon the state-of-the-art on most metrics, and showcase our approach on real-world object captures.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03163
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ROGR: Relightable 3D Objects using Generative Relighting
Tang, Jiapeng
Levine, Matthew
Verbin, Dor
Garbin, Stephan J.
Nießner, Matthias
Brualla, Ricardo Martin
Srinivasan, Pratul P.
Henzler, Philipp
Computer Vision and Pattern Recognition
Graphics
We introduce ROGR, a novel approach that reconstructs a relightable 3D model of an object captured from multiple views, driven by a generative relighting model that simulates the effects of placing the object under novel environment illuminations. Our method samples the appearance of the object under multiple lighting environments, creating a dataset that is used to train a lighting-conditioned Neural Radiance Field (NeRF) that outputs the object's appearance under any input environmental lighting. The lighting-conditioned NeRF uses a novel dual-branch architecture to encode the general lighting effects and specularities separately. The optimized lighting-conditioned NeRF enables efficient feed-forward relighting under arbitrary environment maps without requiring per-illumination optimization or light transport simulation. We evaluate our approach on the established TensoIR and Stanford-ORB datasets, where it improves upon the state-of-the-art on most metrics, and showcase our approach on real-world object captures.
title ROGR: Relightable 3D Objects using Generative Relighting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2510.03163