LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereo

TL;DR

LUCES-MV introduces a comprehensive real-world multi-view dataset for near-field point light source photometric stereo, enabling improved evaluation and development of robust 3D reconstruction methods.

Contribution

This paper presents the first real-world, multi-view dataset for near-field point light source photometric stereo, including diverse objects, ground truth data, and calibration images.

Findings

State-of-the-art algorithms evaluated on LUCES-MV reveal their strengths and limitations.

The dataset facilitates transparent end-to-end evaluation of photometric stereo methods.

LUCES-MV serves as a benchmark for developing more robust 3D reconstruction techniques.

Abstract

The biggest improvements in Photometric Stereo (PS) field has recently come from adoption of differentiable volumetric rendering techniques such as NeRF or Neural SDF achieving impressive reconstruction error of 0.2mm on DiLiGenT-MV benchmark. However, while there are sizeable datasets for environment lit objects such as Digital Twin Catalogue (DTS), there are only several small Photometric Stereo datasets which often lack challenging objects (simple, smooth, untextured) and practical, small form factor (near-field) light setup. To address this, we propose LUCES-MV, the first real-world, multi-view dataset designed for near-field point light source photometric stereo. Our dataset includes 15 objects with diverse materials, each imaged under varying light conditions from an array of 15 LEDs positioned 30 to 40 centimeters from the camera center. To facilitate transparent end-to-end evaluation, our dataset provides not only ground truth normals and ground truth object meshes and poses but also light and camera calibration images. We evaluate state-of-the-art near-field photometric stereo algorithms, highlighting their strengths and limitations across different material and shape complexities. LUCES-MV dataset offers an important benchmark for developing more robust, accurate and scalable real-world Photometric Stereo based 3D reconstruction methods.