GR3EN: Generative Relighting for 3D Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xing, Xiaoyan, Henzler, Philipp, Hur, Junhwa, Li, Runze, Barron, Jonathan T., Srinivasan, Pratul P., Verbin, Dor
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914290935529472
author Xing, Xiaoyan
Henzler, Philipp
Hur, Junhwa
Li, Runze
Barron, Jonathan T.
Srinivasan, Pratul P.
Verbin, Dor
author_facet Xing, Xiaoyan
Henzler, Philipp
Hur, Junhwa
Li, Runze
Barron, Jonathan T.
Srinivasan, Pratul P.
Verbin, Dor
contents We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable to produce high-quality results on complex real-world scenes. Though recent progress in using generative image and video diffusion models for relighting has been promising, these techniques are either limited to 2D image and video relighting or 3D relighting of individual objects. Our approach enables controllable 3D relighting of room-scale scenes by distilling the outputs of a video-to-video relighting diffusion model into a 3D reconstruction. This side-steps the need to solve a difficult inverse rendering problem, and results in a flexible system that can relight 3D reconstructions of complex real-world scenes. We validate our approach on both synthetic and real-world datasets to show that it can faithfully render novel views of scenes under new lighting conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16272
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GR3EN: Generative Relighting for 3D Environments
Xing, Xiaoyan
Henzler, Philipp
Hur, Junhwa
Li, Runze
Barron, Jonathan T.
Srinivasan, Pratul P.
Verbin, Dor
Computer Vision and Pattern Recognition
We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable to produce high-quality results on complex real-world scenes. Though recent progress in using generative image and video diffusion models for relighting has been promising, these techniques are either limited to 2D image and video relighting or 3D relighting of individual objects. Our approach enables controllable 3D relighting of room-scale scenes by distilling the outputs of a video-to-video relighting diffusion model into a 3D reconstruction. This side-steps the need to solve a difficult inverse rendering problem, and results in a flexible system that can relight 3D reconstructions of complex real-world scenes. We validate our approach on both synthetic and real-world datasets to show that it can faithfully render novel views of scenes under new lighting conditions.
title GR3EN: Generative Relighting for 3D Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.16272