cs.CVNov 1, 2026

LUMEN: Geometry-Guided Diffusion Model for Spatially-Varying HDR Illumination Estimation

Authors: Hongze Chen, Fangyu Lin, Runze Zhang, Lingting Zhu, Weikai Chen, Zeyu Hu, Yingda Yin, Keyang Luo, 

Organizations: The Hong Kong University of Science and Technology, Hong Kong · LIGHTSPEED, China · Lingnan University, Hong Kong

Abstract

Estimating scene illumination from images is challenging as lighting is inherently spatially varying, depending on geometry, occlusion, and light sources. Existing methods incorporate geometric cues by deriving local environment maps or probe-based representations, but largely rely on regression or parametric models, resulting in over-smoothed lighting and limited realism. We revisit spatially-varying illumination estimation from a generative perspective and introduce LUMEN, a geometry-conditioned diffusion framework for synthesizing high-dynamic-range (HDR) environment maps at arbitrary spatial locations from single or multi-view images. Specifically, we reconstruct a coarse 3D scene from input images and render partial environment maps at arbitrary locations to encode visibility and spatial structure. These signals are fused with multi-view image features and fed into a diffusion transformer to generate full HDR environment maps. To train the model, we build a synthetic dataset of 700 indoor scenes with dense spatial supervision, including multi-view RGB images, depth, and HDR illumination at multiple sampled locations. This dataset enables the model to learn spatially consistent lighting distributions across diverse scenes. Extensive experiments demonstrate that LUMEN significantly improves visual fidelity and spatial coherence compared to prior approaches.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Video Generation Models Are Inherent Lighting Estimators

    Jul 6, 2026Ziqi Cai, Shuchen Weng, Kaiqi Liu +5Video Diffusion ModelsHDR Imaging

  2. RoomLight: A 2.5D Illumination Prior for Indoor Environments

    Sep 23, 2026Andreea Ardelean, Bernhard EggerInverse Rendering

  3. Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting

    Jul 9, 2026Chenjian Gao, Linning Xu, Tianfan XueMulti-View ConsistencyImage Relighting