Research map / Image generation / Super-resolution
Photometric Depth Super-Resolution
Bjoern Haefner, Songyou Peng, Alok Verma, Yvain Quéau, Daniel Cremers
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 joint shape-from-shading depth super-resolution instead of competing methods | single-shot depth SR · synthetic, scale factor 2 | mean angular error: 36.9999 -> 21.1126 | Improved |
| use joint shape-from-shading depth super-resolution instead of competing methods | single-shot depth SR · synthetic, scale factor 4 | mean angular error: 41.0238 -> 23.9521 | Improved |
| use joint shape-from-shading depth super-resolution instead of competing methods | single-shot depth SR · synthetic, scale factor 8 | mean angular error: 43.9022 -> 26.4768 | Improved |
| use joint shape-from-shading depth super-resolution instead of competing methods | single-shot depth SR · synthetic, scale factor 2 | depth RMSE: 0.048392 -> 0.044394 | Improved |
| use joint shape-from-shading depth super-resolution instead of competing methods | single-shot depth SR · synthetic, scale factor 4 | depth RMSE: 0.059342 -> 0.068779 | Hurt |
| use joint shape-from-shading depth super-resolution instead of competing methods | single-shot depth SR · synthetic, scale factor 8 | depth RMSE: 0.084754 -> 0.1078 | Hurt |
| increase scale factor from 2 to 8 (ablation) | single-shot depth SR · synthetic | mean angular error: 21.1126 -> 26.4768 | Hurt |
| large values of the depth-fidelity weight mu (ablation) | single-shot depth SR · Joyful Yell synthetic | albedo/depth RMSE | Hurt |
Closest papers by meaning
- Deep Learning Methods for Calibrated Photometric Stereo and Beyond (TPAMI 2024 · similarity 0.90)
- Deep near-light photometric stereo for spatially varying reflectances (ECCV 2020 · similarity 0.90)
- Variational Uncalibrated Photometric Stereo Under General Lighting (ICCV 2019 · similarity 0.90)
- Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading (CVPR 2018 · similarity 0.89)
- DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images (ECCV 2022 · similarity 0.89)
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · 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.
