Research map / 3D vision / Depth and stereo
Multi-View Azimuth Stereo via Tangent Space Consistency
Read the paperCheck 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 multi-view tangent consistency rather than a single-view tangent loss (ablation) | MVAS · 3D shape reconstruction | shape ambiguity | Helped |
| Handle the polarization azimuth half-pi ambiguity by allowing both candidate tangent vectors (ablation) | MVAS with polarization imaging · Polarization imaging reconstruction | reconstruction quality | Helped |
| Reduce input viewpoints from 15 to 10 (ablation) | MVAS · DiLiGenT-MV, Buddha | Chamfer distance: 0.357 -> 0.372 | Hurt |
| Reduce input viewpoints from 15 to 8 (ablation) | MVAS · DiLiGenT-MV, Buddha | Chamfer distance: 0.357 -> 0.449 | Hurt |
| Reduce input viewpoints from 15 to 6 (ablation) | MVAS · DiLiGenT-MV, Buddha | Chamfer distance: 0.357 -> 0.424 | Hurt |
| Reduce input viewpoints from 15 to 5 (ablation) | MVAS · DiLiGenT-MV, Buddha | Chamfer distance: 0.357 -> 0.422 | Hurt |
| Use MVAS instead of PS-NeRF | DiLiGenT-MV normal reconstruction · Cow | MAE: 4.35 -> 3.72 | Helped |
| Use MVAS instead of PS-NeRF | DiLiGenT-MV normal reconstruction · Reading | MAE: 9.36 -> 10.02 | Hurt |
| Use MVAS instead of PS-NeRF | DiLiGenT-MV geometry reconstruction · Cow | Chamfer distance: 0.287 -> 0.216 | Helped |
| Use MVAS instead of PS-NeRF | DiLiGenT-MV geometry reconstruction · Reading | Chamfer distance: 0.352 -> 0.522 | Hurt |
Closest papers by meaning
- RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction (CVPR 2024 · similarity 0.85)
- MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction (CVPR 2024 · similarity 0.85)
- PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction (CVPR 2025 · similarity 0.84)
- NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images (CVPR 2024 · similarity 0.83)
- SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration (CVPR 2024 · similarity 0.83)
- UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets (CVPR 2024 · similarity 0.83)
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.