Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting
2026-07-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present Lume-Palette, a method to change indoor lighting in images while keeping everything looking realistic and consistent from multiple viewpoints. They split the task into two parts: first, they capture lighting styles from an existing model, then they place lights in 3D space based on rough room shapes. Their system smartly uses important spatial information to handle many views without getting overwhelmed. Tests show it produces believable and controllable lighting changes in both synthetic and real scenes.
indoor scene relightingdiffusion modelssemantic lightingmulti-view consistencyillumination distillationillumination casting3D geometrymulti-modal inputsspatial controlphotorealism
Authors
Chenjian Gao, Linning Xu, Tianfan Xue
Abstract
Indoor scene relighting demands photorealism, precise spatial control, and strict multi-view consistency. While diffusion-based image editing models enable semantic lighting manipulation via text prompts, enforcing exact 3D light placement often disrupts their generative priors. We propose Lume-Palette, a progressive framework that leverages semantic lighting priors for spatially controllable multi-view indoor relighting. The approach decouples relighting into two stages: (1) illumination distillation, which extracts canonical illumination palettes from a pretrained diffusion model to preserve realistic material-light interactions, and (2) illumination casting, which explicitly maps target spatial lighting conditions defined from coarse 3D geometry. To efficiently handle dense multi-view and multi-modal inputs, we introduce an asymmetric multi-view conditioning strategy that selectively injects essential spatial context. Experiments on diverse synthetic scenes and real-world scenes demonstrate that Lume-Palette produces photorealistic, spatially controllable, and multi-view consistent relighting results. Project Page: https://cjeen.github.io/lumepalette