Research map / 3D vision / Depth and stereo
Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance
Hang Zhang, Kristin Dana, Ko Nishino
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 DRC-opt hashing instead of directly hashing CNN activations (CNN-ITQ) | hash codes · Reflectance disks | recognition precision (%): 51.9 -> 60.2 | Improved |
| use DRC-opt instead of FV-SIFT-Hash | hash codes · Reflectance disks | recognition precision (%): 64.5 -> 60.2 | Hurt |
| use DRC-opt instead of FV-SIFT-Hash | hash codes · FMD | recognition precision (%): 48.3 -> 65.5 | Improved |
| use DRC-opt instead of FV-SIFT-Hash | hash codes · DTD | recognition precision (%): 43.6 -> 55.8 | Improved |
| use DRC-opt instead of FV-SIFT-Hash | hash codes · KTH | recognition precision (%): 72.0 -> 77.2 | Improved |
| use optimized DRC-opt instead of random DRC (ablation) | DRC · DTD | recognition precision (%): 55.4 -> 55.8 | Improved |
| use optimized DRC-opt instead of random DRC (ablation) | DRC · Reflectance disks | recognition precision (%): 59.9 -> 60.2 | No clear effect |
| use DRC retrieval instead of neural net regression for friction | DRC · Reflectance-friction | mean percentage error (%): 14.74 -> 11.15 | Improved |
| use FV pooling of CNN activations instead of VLAD (ablation) | KBE hashing · KTH | recognition precision (%): 75.6 -> 74.4 | No clear effect |
Closest papers by meaning
- Reflectance and Natural Illumination from Single-Material Specular Objects Using Deep Learning (TPAMI 2017 · similarity 0.86)
- A Lightweight Approach for On-The-Fly Reflectance Estimation (ICCV 2017 · similarity 0.86)
- Reflectance Capture Using Univariate Sampling of BRDFs (ICCV 2017 · similarity 0.86)
- Deep Reflectance Maps (CVPR 2016 · similarity 0.85)
- Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior (CVPR 2024 · similarity 0.85)
- Real-Time Neural BRDF with Spherically Distributed Primitives (CVPR 2024 · similarity 0.84)
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.
