Research map / 3D vision / Depth and stereo
DiLiGenT102: A Photometric Stereo Benchmark Dataset With Controlled Shape and Material Variation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Evaluate methods across a controlled 10-shape by 10-material real-world benchmark | Photometric stereo methods · DiLiGenT102 | mean angular error | Mixed |
| Use TH46 instead of other non-learning methods | Non-learning photometric stereo · DiLiGenT102 | median angular error: 16.18 | Helped |
| Use learning-based methods rather than non-learning methods | Photometric stereo · DiLiGenT102 | mean angular error | Mixed |
| Use calibrated lighting rather than uncalibrated lighting | Photometric stereo · DiLiGenT102 | mean angular error | Helped |
| Improve modeling of global illumination effects such as cast shadows and inter-reflections | Photometric stereo · DiLiGenT102 TURBINE | mean angular error | Helped |
| Improve training coverage of rough-surface BRDFs | Learning-based photometric stereo · DiLiGenT102 | mean angular error | Helped |
Closest papers by meaning
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo (CVPR 2016 · similarity 0.92)
- DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency (CVPR 2024 · similarity 0.91)
- Universal Photometric Stereo Network Using Global Lighting Contexts (CVPR 2022 · similarity 0.89)
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · similarity 0.85)
- Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images (CVPR 2025 · similarity 0.85)
- Differentiable Display Photometric Stereo (CVPR 2024 · similarity 0.84)
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.