SyncLight: Single-Edit Multi-View Relighting

TL;DR

SyncLight is a novel multi-view relighting method that ensures consistent, high-fidelity lighting control across uncalibrated views using a diffusion transformer trained on synthetic and real data.

Contribution

It introduces a multi-view diffusion transformer trained with a latent bridge matching formulation for zero-shot, multi-view relighting without camera calibration.

Findings

Achieves high-fidelity relighting in a single inference step.

Generalizes zero-shot to any number of viewpoints.

Trained on a large hybrid dataset of synthetic and real multi-view scenes.

Abstract

We present SyncLight, a method to enable consistent, parametric control over light sources across multiple uncalibrated views of a static scene conditioned on a single view. While single-view relighting has advanced significantly, existing generative approaches struggle to maintain the rigorous lighting consistency essential for multi-camera broadcasts, stereoscopic cinema, and virtual production. SyncLight addresses this by enabling precise control over light intensity and color across a multi-view capture of a scene, conditioned on a single reference edit. Our method leverages a multi-view diffusion transformer trained using a latent bridge matching formulation, achieving high-fidelity relighting of the entire image set in a single inference step. To facilitate training, we introduce a large-scale hybrid dataset comprising diverse synthetic environments -- curated from existing sources and newly designed scenes -- alongside high-fidelity, real-world multi-view captures under calibrated illumination. Though trained only on image pairs, SyncLight generalizes zero-shot to an arbitrary number of viewpoints, effectively propagating lighting changes across all views, without requiring camera pose information. SyncLight enables practical relighting workflows for multi-view capture systems.