Research map / 3D vision / Depth and stereo
Depth From a Polarisation + RGB Stereo Pair
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 |
|---|---|---|---|
| Combine stereo guide depth with polarisation normals, albedo estimation, and perspective depth estimation | Proposed method · Synthetic data, σ=0% | mean absolute depth difference (mm): 0.49 -> 0.29 | Helped |
| Combine stereo guide depth with polarisation normals, albedo estimation, and perspective depth estimation | Proposed method · Synthetic data, σ=0% | mean angular surface normal error (deg): 38.151 -> 9.799 | Helped |
| Combine stereo guide depth with polarisation normals, albedo estimation, and perspective depth estimation | Proposed method · Synthetic data, σ=0.5% | mean absolute depth difference (mm): 0.49 -> 0.30 | Helped |
| Combine stereo guide depth with polarisation normals, albedo estimation, and perspective depth estimation | Proposed method · Synthetic data, σ=1% | mean angular surface normal error (deg): 39.67 -> 14.03 | Helped |
| Set albedo gradient regularisation λI=3 instead of λI=0 (ablation) | Proposed method · Synthetic data | albedo smoothness | Helped |
| Set albedo gradient regularisation λI=3 instead of λI=0 (ablation) | Proposed method · Synthetic data | geometry detail preservation | Mixed |
Closest papers by meaning
- Polarimetric Multi-View Stereo (CVPR 2017 · similarity 0.90)
- PolarDepth: Monocular Transparent Object Depth from Polar-Physics Priors (ICML 2026 · similarity 0.88)
- Polarimetric Normal Stereo (CVPR 2021 · similarity 0.87)
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · similarity 0.86)
- Robust Depth Enhancement via Polarization Prompt Fusion Tuning (CVPR 2024 · similarity 0.86)
- Glossy Object Reconstruction with Cost-effective Polarized Acquisition (CVPR 2025 · similarity 0.85)
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.