We present a novel approach for interactive light editing in indoor scenes from a single multi-view scene capture. Our method leverages a generative image-based light decomposition model that factorizes complex indoor scene illumination into its constituent light sources. This factorization enables independent manipulation of individual light sources, specifically allowing control over their state (on/off), chromaticity, and intensity. We further introduce multi-view lighting harmonization to ensure consistent propagation of the lighting decomposition across all scene views. This is integrated into a relightable 3D Gaussian splatting representation, providing real-time interactive control over the individual light sources. Our results demonstrate highly photorealistic lighting decomposition and relighting outcomes across diverse indoor scenes. We evaluate our method on both synthetic and real-world datasets and provide a quantitative and qualitative comparison to state-of-the-art techniques.
Given a multi-view capture of an indoor scene, we apply our single-image lighting decomposition model to generate one-light-at-a-time (OLAT) decompositions. We propagate these decompositions across all views using multi-view lighting harmonization with geometric constraints. Repeating this for each light source yields a complete multi-view OLAT dataset. We train a relightable 3D Gaussian splatting representation on these decompositions, enabling real-time interactive control over each light from any viewpoint.
Our method decomposes complex scene lighting into individually controllable light sources from a single image.
We consistently propagate lighting decompositions across all scene views using multi-view lighting harmonization.
Our relightable 3D Gaussian splatting representation enables real-time interactive manipulation of individual light sources.
Use the controls below to interactively remix the lighting of various scenes. You can adjust the intensity and color of individual light sources, change the ambient light, and download your result.
@unpublished{liang2026luxremix,
title = {{LuxRemix}: Lighting Decomposition and Remixing for Indoor Scenes},
author = {Ruofan Liang and Normal M{\"u}ller and Ethan Weber and Duncan Zauss and
Nandita Vijaykumar and Peter Kontschieder and Christian Richardt},
note = {arXiv},
year = {2026},
}