Research map / 3D vision / Depth and stereo
A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 WG10 or IW12 instead of BASELINE | Calibrated non-Lambertian photometric stereo · BALL, CAT, POT1 | mean angular error | Helped |
| Use WG10 or IW12 instead of BASELINE | Calibrated non-Lambertian photometric stereo · POT2, COW | mean angular error | Hurt |
| Fit a mixture of Ward reflectance models | GC10 · POT2, COW | mean angular error | Helped |
| Fit a mixture of Ward reflectance models | GC10 · GOBLET, BUDDHA, READING | mean angular error | Hurt |
| Use the bivariate BRDF constraint | AZ08 · DiLiGenT objects with sparse or weak highlights | mean angular error | Helped |
| Assume a one-dimensional monotonic BRDF | ST12 · BALL, BEAR | mean angular error | Hurt |
| Assume a one-dimensional monotonic BRDF | ST12 · COW | mean angular error | Helped |
| Use the single-lobe monotonic reflectance assumption | HM10 · GOBLET | mean angular error | Helped |
| Use the single-lobe monotonic reflectance assumption | HM10 · BEAR, POT2 | mean angular error | Hurt |
| Use the recent bivariate BRDF representations | ST14 and IA14 · Most DiLiGenT objects | mean angular error | Helped |
| Discard bottom- and top-ranked intensity observations before applying BASELINE (ablation) | Position-threshold method · Most DiLiGenT objects | mean angular error | Helped |
| Use the tightest tested intensity thresholds (Tlow = 40%, Thigh = 60%) (ablation) | Position-threshold method · DiLiGenT | mean angular error | Helped |
Closest papers by meaning
- DiLiGenT102: A Photometric Stereo Benchmark Dataset With Controlled Shape and Material Variation (CVPR 2022 · similarity 0.92)
- DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency (CVPR 2024 · similarity 0.91)
- Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo (CVPR 2024 · similarity 0.88)
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · similarity 0.86)
- Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo (CVPR 2024 · similarity 0.86)
- Differentiable Display Photometric Stereo (CVPR 2024 · similarity 0.86)
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.