Near-Light Color Photometric Stereo for Mono-Chromatic Non-Lambertian Surfaces

2026-01-19

AI Summary

This work addresses the ill-posed problem of high-fidelity 3D reconstruction from a single color image under near-point lighting and non-Lambertian reflectance, conditions under which existing photometric stereo methods struggle. To this end, we propose the first approach that leverages neural implicit representations to jointly model surface geometry and spatially varying BRDF. By incorporating a chromaticity constancy prior, our method enhances solution uniqueness without requiring multi-view or multi-light observations. The resulting framework enables robust reconstruction from a single RGB image and is validated through a custom-designed compact optical tactile sensor in real-world scenarios. Extensive experiments on both synthetic and real datasets demonstrate that our method significantly outperforms state-of-the-art techniques in terms of accuracy and practical applicability.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Color photometric stereo enables single-shot surface reconstruction, extending conventional photometric stereo that requires multiple images of a static scene under varying illumination to dynamic scenarios. However, most existing approaches assume ideal distant lighting and Lambertian reflectance, leaving more practical near-light conditions and non-Lambertian surfaces underexplored. To overcome this limitation, we propose a framework that leverages neural implicit representations for depth and BRDF modeling under the assumption of mono-chromaticity (uniform chromaticity and homogeneous material), which alleviates the inherent ill-posedness of color photometric stereo and allows for detailed surface recovery from just one image. Furthermore, we design a compact optical tactile sensor to validate our approach. Experiments on both synthetic and real-world datasets demonstrate that our method achieves accurate and robust surface reconstruction.

Problem

• near-light
• non-Lambertian
• color photometric stereo
• surface reconstruction
• mono-chromaticity

Innovation

• neural implicit representation
• color photometric stereo
• non-Lambertian surface
• near-light condition
• mono-chromaticity