Research map / 3D vision / Depth and stereo
Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Composition
Satoshi Ikehata, Yuta Asano
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 SpectraM-PS physics-free network trained on RGB-rendered PS-Multiplex instead of calibrated physics-based methods | SpectraM-PS · SpectraM14 Condition 1 | mean angular error (deg): 17.1 -> 8.9 | Improved |
| increase channel crosstalk (Condition 1 to 3) for SpectraM-PS | SpectraM-PS · SpectraM14 | mean angular error (deg): 8.9 -> 11.6 | Hurt |
| increase channel crosstalk (Condition 1 to 3) for Guo et al. | Guo et al. · SpectraM14 | mean angular error (deg): 18.9 -> 51.7 | Hurt |
| train on RGB-only narrowband rendered data then test on NIR sensors | SpectraM-PS · SpectraM14 Condition 4 (NIR) | mean angular error (deg): 19.1 -> 8.4 | Improved |
| SpectraM-PS vs SDM-UniPS trained on PS-Multiplex (dual-scale decoder with patch embedding) (ablation) | SpectraM-PS · synthetic spectrally multiplexed scenes | mean angular error (deg) | Improved |
| SpectraM-PS is slower than Lv et al. at inference | SpectraM-PS · SpectraM14 Conditions 2 and 3 | inference time (sec): 0.46 -> 3.42 | Hurt |
Closest papers by meaning
- A Microfacet-Based Reflectance Model for Photometric Stereo With Highly Specular Surfaces (ICCV 2017 · similarity 0.89)
- Multispectral Photometric Stereo for Spatially-Varying Spectral Reflectances: A Well Posed Problem? (CVPR 2021 · similarity 0.88)
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo (CVPR 2016 · similarity 0.88)
- Uncalibrated Photometric Stereo by Stepwise Optimization Using Principal Components of Isotropic BRDFs (CVPR 2016 · similarity 0.88)
- Deep Photometric Stereo for Non-Lambertian Surfaces (TPAMI 2020 · similarity 0.88)
- Patch-Based Uncalibrated Photometric Stereo Under Natural Illumination (TPAMI 2021 · similarity 0.88)
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.
