UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Kai, Liang, Ruofan, Munkberg, Jacob, Hasselgren, Jon, Vijaykumar, Nandita, Keller, Alexander, Fidler, Sanja, Gilitschenski, Igor, Gojcic, Zan, Wang, Zian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912438591422464
author He, Kai
Liang, Ruofan
Munkberg, Jacob
Hasselgren, Jon
Vijaykumar, Nandita
Keller, Alexander
Fidler, Sanja
Gilitschenski, Igor
Gojcic, Zan
Wang, Zian
author_facet He, Kai
Liang, Ruofan
Munkberg, Jacob
Hasselgren, Jon
Vijaykumar, Nandita
Keller, Alexander
Fidler, Sanja
Gilitschenski, Igor
Gojcic, Zan
Wang, Zian
contents We address the challenge of relighting a single image or video, a task that demands precise scene intrinsic understanding and high-quality light transport synthesis. Existing end-to-end relighting models are often limited by the scarcity of paired multi-illumination data, restricting their ability to generalize across diverse scenes. Conversely, two-stage pipelines that combine inverse and forward rendering can mitigate data requirements but are susceptible to error accumulation and often fail to produce realistic outputs under complex lighting conditions or with sophisticated materials. In this work, we introduce a general-purpose approach that jointly estimates albedo and synthesizes relit outputs in a single pass, harnessing the generative capabilities of video diffusion models. This joint formulation enhances implicit scene comprehension and facilitates the creation of realistic lighting effects and intricate material interactions, such as shadows, reflections, and transparency. Trained on synthetic multi-illumination data and extensive automatically labeled real-world videos, our model demonstrates strong generalization across diverse domains and surpasses previous methods in both visual fidelity and temporal consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15673
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
He, Kai
Liang, Ruofan
Munkberg, Jacob
Hasselgren, Jon
Vijaykumar, Nandita
Keller, Alexander
Fidler, Sanja
Gilitschenski, Igor
Gojcic, Zan
Wang, Zian
Computer Vision and Pattern Recognition
We address the challenge of relighting a single image or video, a task that demands precise scene intrinsic understanding and high-quality light transport synthesis. Existing end-to-end relighting models are often limited by the scarcity of paired multi-illumination data, restricting their ability to generalize across diverse scenes. Conversely, two-stage pipelines that combine inverse and forward rendering can mitigate data requirements but are susceptible to error accumulation and often fail to produce realistic outputs under complex lighting conditions or with sophisticated materials. In this work, we introduce a general-purpose approach that jointly estimates albedo and synthesizes relit outputs in a single pass, harnessing the generative capabilities of video diffusion models. This joint formulation enhances implicit scene comprehension and facilitates the creation of realistic lighting effects and intricate material interactions, such as shadows, reflections, and transparency. Trained on synthetic multi-illumination data and extensive automatically labeled real-world videos, our model demonstrates strong generalization across diverse domains and surpasses previous methods in both visual fidelity and temporal consistency.
title UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.15673