Research map / 3D vision / Depth and stereo
A CNN Based Approach for the Point-Light Photometric Stereo Problem
Fotios Logothetis, Roberto Mecca, Ignas Budvytis, Roberto Cipolla
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 |
|---|---|---|---|
| add point-light attenuation compensation (ablation) | PX-NET · LUCES (real) | mean angular error: 19.88 -> 12.39 | Improved |
| add point-light attenuation compensation (ablation) | PX-NET · LUCES (real) | mean depth error: 6.09 -> 3.09 | Improved |
| add point-light compensation (ablation) | PX-NET · DiLiGenT (real) | mean angular error: 6.28 -> 5.85 | Improved |
| train setup-specific network instead of setup-agnostic | Ours · LUCES (real) | mean angular error: 9.87 -> 9.59 | Improved |
| train setup-specific network instead of general | Ours · DiLiGenT (real) | mean angular error: 5.89 -> 5.66 | Improved |
| evaluate at full resolution instead of quarter | Ours - General · LUCES (real) | mean angular error: 9.87 -> 9.90 | No clear effect |
| use 15 lights instead of 52 | Ours · Synthetic LUCES | mean angular error: 7.1 -> 6.1 | No clear effect |
| reduce focal length to simulate fish-eye (LUCES-0.25f) | Ours · Synthetic LUCES | error | No clear effect |
| add second refinement iteration (ablation) | Ours · Synthetic LUCES | error | No clear effect |
| initialize with ground-truth depth instead of planar estimate (ablation) | Ours · Synthetic LUCES | normal error | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PX-NET — PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks (ICCV 2021) · better on 1 of 1 shared result
- SPLINE-Net — SPLINE-Net: Sparse Photometric Stereo Through Lighting Interpolation and Normal Estimation Networks (ICCV 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfaces (ECCV 2018 · similarity 0.93)
- Deep Learning Methods for Calibrated Photometric Stereo and Beyond (TPAMI 2024 · similarity 0.93)
- Deep Photometric Stereo for Non-Lambertian Surfaces (TPAMI 2020 · similarity 0.92)
- DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images (ECCV 2022 · similarity 0.92)
- PS-FCN: A Flexible Learning Framework for Photometric Stereo (ECCV 2018 · similarity 0.91)
- Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo (CVPR 2024 · similarity 0.90)
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.
