Event-based Photometric Stereo via Rotating Illumination and Per-Pixel Learning

2026-03-11

AI Summary

This work addresses the limitations of traditional photometric stereo, which relies on controlled multi-light setups and is highly susceptible to ambient illumination, particularly under high-dynamic or continuously varying lighting conditions. The paper introduces a novel, compact photometric stereo framework that uniquely combines an event camera with a single circumferentially rotating light source, eliminating the need for explicit system calibration. A lightweight per-pixel neural network is employed to directly predict surface normals from the asynchronous event stream. The proposed method operates without synchronized multi-lighting and demonstrates robustness in challenging scenarios, including sparse events, strong ambient light, and specular regions. Experimental results on both public and newly collected real-world datasets show a 7.12% reduction in mean angular error compared to existing event-based photometric stereo approaches.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Photometric stereo is a technique for estimating surface normals using images captured under varying illumination. However, conventional frame-based photometric stereo methods are limited in real-world applications due to their reliance on controlled lighting, and susceptibility to ambient illumination. To address these limitations, we propose an event-based photometric stereo system that leverages an event camera, which is effective in scenarios with continuously varying scene radiance and high dynamic range conditions. Our setup employs a single light source moving along a predefined circular trajectory, eliminating the need for multiple synchronized light sources and enabling a more compact and scalable design. We further introduce a lightweight per-pixel multi-layer neural network that directly predicts surface normals from event signals generated by intensity changes as the light source rotates, without system calibration. Experimental results on benchmark datasets and real-world data collected with our data acquisition system demonstrate the effectiveness of our method, achieving a 7.12\% reduction in mean angular error compared to existing event-based photometric stereo methods. In addition, our method demonstrates robustness in regions with sparse event activity, strong ambient illumination, and scenes affected by specularities.

Problem

• photometric stereo
• event camera
• ambient illumination
• surface normal estimation
• real-world applications

Innovation

• event-based vision
• photometric stereo
• rotating illumination
• per-pixel learning
• surface normal estimation