Work

PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization

Year: 2025

Type: conference-paper

Abstract: This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, interreflections, and lack of constraints on the surface reflectance, leading to inaccurate decomposition of reflectance and illumination due to the ill-posed nature of inverse rendering. In this work, we propose a new method for neural inverse rendering. Our method jointly optimizes the light source position to account for the self-shadows in images, and computes indirect illumination using a differentiable rendering layer and an importance sampling strategy. To enhance surface reflectance decomposition, we introduce a new regularization by distilling DINO features to foster accurate and consistent material decomposition. Extensive experiments on synthetic and real datasets demonstrate that our method outperforms the state-of-the-art methods in reflectance decomposition.

Source: International Conference on 3D Vision (3DV)

DOI: 10.1109/3dv66043.2025.00055

Authors: Jingzhi Bao, Guanying Chen, Shuguang Cui

Institution: Chinese University of Hong Kong, Shenzhen

Language: English

Topic: Computer Graphics and Visualization Techniques

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

Award: G6352250275