SyncLight: Single-Edit Multi-View Relighting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Serrano-Lozano, David, Bhattad, Anand, Herranz, Luis, Lalonde, Jean-François, Vazquez-Corral, Javier
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910220350914560
author Serrano-Lozano, David
Bhattad, Anand
Herranz, Luis
Lalonde, Jean-François
Vazquez-Corral, Javier
author_facet Serrano-Lozano, David
Bhattad, Anand
Herranz, Luis
Lalonde, Jean-François
Vazquez-Corral, Javier
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16981
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SyncLight: Single-Edit Multi-View Relighting
Serrano-Lozano, David
Bhattad, Anand
Herranz, Luis
Lalonde, Jean-François
Vazquez-Corral, Javier
Computer Vision and Pattern Recognition
Graphics
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.
title SyncLight: Single-Edit Multi-View Relighting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2601.16981