Bedroom








Inverse rendering of indoor scenes remains challenging due to the ambiguity between reflectance and lighting, exacerbated by inter-reflections among multiple objects. While natural illumination-based methods struggle to resolve this ambiguity, co-located light-camera setups offer better disentanglement as lighting can be easily calibrated via Structure-from-Motion. However, such setups introduce additional complexities like strong inter-reflections, dynamic shadows, near-field lighting, and moving specular highlights, which existing approaches fail to handle. We present GLOW, a Global Illumination-aware Inverse Rendering framework designed to address these challenges. GLOW integrates a neural implicit surface representation with a neural radiance cache to approximate global illumination, jointly optimizing geometry and reflectance through carefully designed regularization and initialization. We then introduce a dynamic radiance cache that adapts to sharp lighting discontinuities from near-field motion, and a surface-angle-weighted radiometric loss to suppress specular artifacts common in flashlight captures. Experiments show that GLOW substantially outperforms prior methods in material reflectance estimation under both natural and co-located illumination.
Comparison of our technique against natural-illumination and co-located light and camera baselines on synthetic data.
Comparison of our technique against co-located light and camera baselines on real captures.
The ablation isolates the radiance-cache design on the kitchen scene using ground-truth mesh geometry, with reflectance error and runtime below.































































































Quantitative results on ablation of radiance cache.
| Path | Ours | Direct | Naive Cache | |
|---|---|---|---|---|
| Albedo | 0.38 | 0.35 | 7.21 | 4.97 |
| Roughness | 7.46 | 6.11 | 304.8 | 235.6 |
| Runtime | 3097 | 821 | 453 | 794 |
Qualitative and quantitative radiance-cache ablation on the kitchen scene using ground-truth mesh geometry. Albedo and roughness are reported as MSE x103; runtime is reported in minutes.
@article{wu2026glow,
title={GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light and Camera},
author={Wu, Jiaye and Hadadan, Saeed and Lin, Geng and Tu, Peihan and Zwicker, Matthias and Jacobs, David and Sengupta, Roni},
journal={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2026}
}