LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes

2026-01-21

AI Summary

This work proposes a generative image-based method for lighting decomposition that, for the first time, enables disentanglement and real-time interactive editing of complex illumination from a single multi-view capture of an indoor scene. By decomposing scene lighting into independently controllable light sources and introducing a multi-view lighting consistency mechanism to preserve view coherence, the approach is integrated into a relightable 3D Gaussian splatting representation. Experiments demonstrate that the method outperforms state-of-the-art techniques in both lighting decomposition accuracy and relighting quality across diverse real-world and synthetic indoor scenes, enabling efficient and photorealistic editing of light source states, chromaticity, and intensity.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Multi-instance/Multi-view Learning
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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. For video results and interactive demos, see https://luxremix.github.io.

Problem

• lighting decomposition
• indoor scenes
• relighting
• multi-view consistency
• interactive light editing

Innovation

• lighting decomposition
• relightable 3D representation
• 3D Gaussian splatting
• multi-view harmonization
• interactive relighting