UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

TL;DR

UniRelight presents a novel joint decomposition and synthesis method using video diffusion models to improve single-image and video relighting, achieving better realism and generalization across diverse scenes.

Contribution

It introduces a unified approach that estimates albedo and synthesizes relighting in one pass, overcoming data limitations and enhancing scene understanding.

Findings

Outperforms previous methods in visual fidelity

Demonstrates strong generalization across domains

Achieves high temporal consistency

Abstract

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.