Research map / 3D vision / Depth and stereo
DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
Ashish Tiwari, Shanmuganathan Raman
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 lighting estimation (ablation) | DeepPS2 base · DiLiGenT average | MAE (deg): 26.07 -> 18.51 | Improved |
| add albedo refinement module (ablation) | DeepPS2 with lighting estimation · DiLiGenT average | MAE (deg): 18.51 -> 15.85 | Improved |
| add positional encoding (ablation) | DeepPS2 with albedo refinement · DiLiGenT average | MAE (deg): 15.85 -> 14.55 | Improved |
| add image relighting module (ablation) | DeepPS2 with positional encoding · DiLiGenT average | MAE (deg): 14.55 -> 13.44 | Improved |
| add weak-supervision warm-up at early training (ablation) | DeepPS2 · DiLiGenT average | MAE (deg): 27.33 -> 13.44 | Improved |
| provide one frontally-lit image with known lighting (ablation) | DeepPS2 · DiLiGenT average | MAE (deg): 13.44 -> 13.24 | Improved |
| use full ground-truth supervision (ablation) | DeepPS2 · DiLiGenT average | MAE (deg): 13.44 -> 11.98 | Improved |
| use calibrated lighting instead of discretized estimated lighting (ablation) | DeepPS2 · DiLiGenT average | MAE (deg): 13.44 -> 12.95 | Improved |
| increase number of light bins K beyond 25 (ablation) | DeepPS2 · DiLiGenT average | MAE (deg) | No clear effect |
Closest papers by meaning
- Deep Learning Methods for Calibrated Photometric Stereo and Beyond (TPAMI 2024 · similarity 0.92)
- Learning to Minify Photometric Stereo (CVPR 2019 · similarity 0.92)
- A CNN Based Approach for the Point-Light Photometric Stereo Problem (IJCV 2022 · similarity 0.92)
- CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfaces (ECCV 2018 · similarity 0.91)
- Self-Calibrating Photometric Stereo by Neural Inverse Rendering (ECCV 2022 · similarity 0.91)
- Universal Photometric Stereo Network Using Global Lighting Contexts (CVPR 2022 · similarity 0.91)
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.
