Research map / 3D vision / Depth and stereo
OpenSubstance: A High-quality Measured Dataset of Multi-View and -Lighting Images and Shapes
Fan Pei, Jinchen Bai, Xiang Feng, Zoubin Bi, Kun Zhou, Hongzhi Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use uncalibrated photometric stereo instead of calibrated under near-field lighting | single-view photometric stereo · OpenSubstance single-view photometric stereo | MAE (deg): 22.33 -> 12.99 | Improved |
| use SuperNormal instead of RNb-NeuS for multi-view shape reconstruction | multi-view photometric stereo · OpenSubstance multi-view photometric stereo (6 objects) | Chamfer distance (mm): 0.698 -> 0.475 | Improved |
| use GS3 instead of NRHints for OLAT relighting | OLAT relighting · OpenSubstance OLAT relighting (5 objects) | LPIPS (avg): 0.120 -> 0.088 | Improved |
| use GaussianShader instead of TensoIR for non-OLAT relighting | non-OLAT relighting · OpenSubstance non-OLAT relighting (10 objects) | PSNR (avg): 27.00 -> 30.94 | Improved |
| use GS3 instead of NRHints for OLAT relighting | OLAT relighting on APPLE object · OpenSubstance OLAT relighting, APPLE | PSNR: 41.08 -> 37.37 | Hurt |
Closest papers by meaning
- OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects (NeurIPS 2023 · similarity 0.89)
- OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation (CVPR 2023 · similarity 0.88)
- Universal Photometric Stereo Network Using Global Lighting Contexts (CVPR 2022 · similarity 0.87)
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo (CVPR 2016 · similarity 0.87)
- A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos (CVPR 2017 · similarity 0.87)
- UniK3D: Universal Camera Monocular 3D Estimation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
