Research map / 3D vision / Depth and stereo
Single Day Outdoor Photometric Stereo
Yannick Hold-Geoffroy, Paulo F. U. Gotardo, Jean‐François Lalonde
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 deep patch-based network instead of calibrated PS | single-day outdoor PS · Synthetic objects, real skies | median error (degrees): 33 -> 14 | Improved |
| use deep patch-based network instead of semi-calibrated Jung et al. | single-day outdoor PS · Synthetic objects, real skies | median error (degrees): 22 -> 14 | Improved |
| add patch context (network on patches) instead of per-pixel DPSN | deep PS · Synthetic objects, real skies | median error | Improved |
| increase input images from 1 to 3 (ablation) | proposed network · Synthetic objects, real skies | normal error | Improved |
| increase input images from 3 to 8 (ablation) | proposed network · Synthetic objects, real skies | normal error | Improved |
| increase input images beyond 8 (ablation) | proposed network · Synthetic objects, real skies | normal error | Hurt |
| increase patch size up to about 14 pixels (ablation) | proposed network · Synthetic objects, real skies | accuracy | Improved |
| increase patch size beyond 14 pixels (ablation) | proposed network · Synthetic objects, real skies | accuracy | Hurt |
| rotate camera away from north (ablation) | proposed network · Synthetic objects, real skies | median error: 5 degrees per 10 degrees | Hurt |
| partial cloud cover on sky | calibrated outdoor PS · HDR sky dataset analysis | confidence interval / conditioning | Improved |
| remove low-rank matrix completion preprocessing (ablation) | Yu et al. calibrated PS · Real owl, partially cloudy day | reconstruction | Improved |
| spatially varying albedo at test time | proposed network · Checkerboard albedo | normal error | Hurt |
Closest papers by meaning
- DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images (ECCV 2022 · similarity 0.90)
- Deep Learning Methods for Calibrated Photometric Stereo and Beyond (TPAMI 2024 · similarity 0.90)
- A CNN Based Approach for the Point-Light Photometric Stereo Problem (IJCV 2022 · similarity 0.89)
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo (CVPR 2016 · similarity 0.89)
- Deep Photometric Stereo for Non-Lambertian Surfaces (TPAMI 2020 · similarity 0.89)
- Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo (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.
