Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Diffusion-Based Material Regularization for Physics-Based Inverse Rendering

About

Reconstructing physics-based 3D assets -- geometry, materials, and illumination -- from multi-view images is a core problem in computer graphics and vision, and a prerequisite for realistic relighting and editing. Physics-based inverse rendering offers an accurate image-formation model, but is severely underconstrained: without strong priors, illumination is baked into materials, and reconstructions generalize poorly to novel views and lighting. Data-driven diffusion models, in contrast, predict visually plausible materials, yet their predictions rarely satisfy the rendering equation and are not directly usable for physics-based rendering. We bridge these two paradigms rather than replacing either. Our key idea is to treat the predictions of a state-of-the-art diffusion model not as target material values but as a similarity kernel for optimization: we introduce a regularization loss that penalizes deviations in the optimized material over surface regions where the diffusion predictions are near-constant, while leaving the optimization free to match the input images. Built on this regularizer, our end-to-end pipeline jointly reconstructs geometry, materials, and illumination, yielding high-quality assets that drop into standard rendering pipelines and relight faithfully. On the Synthetic4Relight, Stanford-ORB, and DTC-Synthetic datasets, our method significantly outperforms state-of-the-art baselines in both reconstruction accuracy and relighting quality.

Jingwang Ling, Lifan Wu, Feng Xu, Shuang Zhao• 2026

Related benchmarks

TaskDatasetResultRank
Geometry EstimationStanfordORB
Depth Error0.25
14
Roughness EstimationSynthetic4Relight (test)
MSE0.013
8
RelightingStanford-ORB (test)
PSNR-H27.22
7
Albedo EstimationSynthetic4Relight
PSNR27.04
4
Aligned Albedo EstimationSynthetic4Relight
PSNR27.83
4
RelightingSynthetic4Relight
PSNR32.02
4
RelightingDTC-Synthetic
PSNR43.21
4
Novel Scene RelightingStanford-ORB
PSNR-H27.22
3
Novel View SynthesisStanford-ORB
PSNR-H29.58
3
Showing 9 of 9 rows

Other info

Follow for update