Research map / 3D vision / Depth and stereo
Shape and Spatially-Varying Reflectance Estimation from Virtual Exemplars
Zhuo Hui, Aswin C. Sankaranarayanan
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 coarse-to-fine search instead of brute force | virtual exemplar normal estimation · synthetic normals, 0.5 deg sampling | time: 74.1s -> 0.41s | Improved |
| use coarse-to-fine search instead of brute force | virtual exemplar normal estimation · synthetic normals, 0.5 deg sampling | angular error: 0.42 -> 0.82 | Hurt |
| add gradient descent refinement (ablation) | coarse-to-fine · synthetic normals, 0.5 deg sampling | angular error: 0.82 -> 0.38 | Improved |
| add gradient descent refinement (ablation) | brute force · synthetic normals, 0.5 deg sampling | angular error: 0.42 -> 0.21 | Improved |
| add gradient descent refinement (ablation) | coarse-to-fine · synthetic normals, 10 deg sampling | angular error: 7.07 -> 4.10 | Improved |
| add gradient descent to coarse-to-fine vs Shi et al. | normal estimation · synthetic MERL, 200 images | angular error: 0.88 -> 0.58 | Improved |
| gradient descent vs competing methods | normal estimation · MERL materials (253 images) | angular error: better in 88 out of 100 materials | Improved |
| gradient descent vs benchmarked methods | normal estimation · photometric stereo benchmark | mean angular error: best on 8 of 10 objects, e.g. harvest 25.44 -> 15.81 | Improved |
| add low-rank prior to per-pixel BRDF estimation (ablation) | BRDF estimation · synthetic spatially-varying sphere | relative BRDF error | Improved |
| use dictionary of mismatched material type (ablation) | normal estimation · MERL 10 test materials, 253 images | angular error | Hurt |
| use leave-one-out dictionary of 99 atoms vs smaller dictionaries (ablation) | normal estimation · MERL 10 test materials | angular error: 99 atoms vs 12 to 23 atoms | Improved |
| reduce dictionary to 10-90 randomly chosen atoms (ablation) | gradient descent normals · MERL, 253 images | angular error: less than 3 deg for most materials | No clear effect |
Closest papers by meaning
- Discrete Search Photometric Stereo for Fast and Accurate Shape Estimation (TPAMI 2022 · similarity 0.93)
- Photometric Stereo via Discrete Hypothesis-and-Test Search (CVPR 2020 · similarity 0.92)
- Shape and Reflectance Estimation in the Wild (TPAMI 2016 · similarity 0.91)
- A Lightweight Approach for On-The-Fly Reflectance Estimation (ICCV 2017 · similarity 0.90)
- SVBRDF-Invariant Shape and Reflectance Estimation from a Light-Field Camera (TPAMI 2017 · similarity 0.90)
- SVBRDF-Invariant Shape and Reflectance Estimation From Light-Field Cameras (CVPR 2016 · similarity 0.89)
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.
