LightSwitch: Multi-view Relighting with Material-guided Diffusion

TL;DR

LightSwitch is a novel diffusion-based framework that efficiently relights multi-view images of objects by leveraging intrinsic material properties, surpassing previous methods in quality and speed.

Contribution

The paper introduces LightSwitch, a scalable, material-guided diffusion approach for multi-view relighting that improves quality and efficiency over existing methods.

Findings

Outperforms previous state-of-the-art relighting priors.

Achieves relighting in as little as 2 minutes.

Effectively handles diverse material compositions.

Abstract

Recent approaches for 3D relighting have shown promise in integrating 2D image relighting generative priors to alter the appearance of a 3D representation while preserving the underlying structure. Nevertheless, generative priors used for 2D relighting that directly relight from an input image do not take advantage of intrinsic properties of the subject that can be inferred or cannot consider multi-view data at scale, leading to subpar relighting. In this paper, we propose Lightswitch, a novel finetuned material-relighting diffusion framework that efficiently relights an arbitrary number of input images to a target lighting condition while incorporating cues from inferred intrinsic properties. By using multi-view and material information cues together with a scalable denoising scheme, our method consistently and efficiently relights dense multi-view data of objects with diverse material compositions. We show that our 2D relighting prediction quality exceeds previous state-of-the-art relighting priors that directly relight from images. We further demonstrate that LightSwitch matches or outperforms state-of-the-art diffusion inverse rendering methods in relighting synthetic and real objects in as little as 2 minutes.