Research map / 3D vision / Depth and stereo
Unbiased Photometric Stereo for Colored Surfaces: A Variational Approach
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 |
|---|---|---|---|
| Use RGB images directly instead of converting them to grayscale | Photometric stereo · Synthetic dataset | mean angular error (MAE) | Helped |
| Use a differential PDE formulation rather than non-differential image ratios | Photometric stereo · Synthetic dataset | mean angular error (MAE) | Helped |
| Solve for all depth values jointly rather than estimating normals locally | Photometric stereo · Synthetic dataset | runtime | Helped |
| Model perspective projection and spatially varying point-light illumination | Variational color photometric stereo · Colored scene, 8 RGB images | reconstruction quality | Helped |
| Use least-squares estimation on off-Lambertian inputs | Variational color photometric stereo · Metallic coins and synthetic human skin | reconstruction quality | Helped |
Closest papers by meaning
- A Non-Convex Variational Approach to Photometric Stereo Under Inaccurate Lighting (CVPR 2017 · similarity 0.88)
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo (CVPR 2016 · similarity 0.88)
- DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency (CVPR 2024 · similarity 0.85)
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · similarity 0.85)
- Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo (CVPR 2024 · similarity 0.85)
- MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction (CVPR 2024 · similarity 0.85)
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.