OpenSubstance: A High-Quality Measured Dataset of Multi-View and -Lighting Images and Shapes

ICCV 2025
Fan Pei, Jinchen Bai, Xiang Feng, Zoubin Bi, Kun Zhou, Hongzhi Wu
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
Corresponding authors
The dataset release is pending university storage allocation due to its substantial size (almost 20 TB). Download access will be available once infrastructure is in place.

Abstract

We present OpenSubstance, a high-quality measured dataset with 2.4 million high-dynamic-range images of 187 objects with a wide variety in shape and appearance, captured under 270 camera views and 1,637 lighting conditions, including 1,620 one-light-at-a-time, 8 environment, 8 linear and 1 full-on illumination. For each image, the corresponding lighting condition, camera parameters and foreground segmentation mask are provided. High-precision 3D geometry is also acquired for rigid objects. It takes 1 hour on average to capture one object with our custom-built high-performance lightstage and a top-grade commercial 3D scanner. We perform comprehensive quantitative evaluation on state-of-the-art techniques across different tasks, including single- and multi-view photometric stereo, as well as relighting.

🔧 Hardware Setup

Custom lightstage with 24,576 high-brightness LEDs, 6 machine vision cameras (5328×4608 resolution), and digital turntable for precise multi-view capture.

💡 Lighting Conditions

1,620 one-light-at-a-time (OLAT), 8 environment maps, 8 linear lighting, and 1 full-on illumination for comprehensive appearance modeling.

📐 3D Scanning

ZEISS ATOS Q Blue-Light 3D scanner with single-digit micron accuracy for high-precision ground truth geometry acquisition.