Research map / 3D vision / Depth and stereo
Uncertainty-Aware Deep Multi-View 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 |
|---|---|---|---|
| combine uncertainty-filtered photometric-stereo normals and multi-view-stereo depths in implicit shape optimization | Uncertainty-Aware Deep MVPS · DiLiGenT-MV average | F-score: 0.974 -> 0.935 | Mixed |
| add both PS and MVS confidence variables to the shape loss (ablation) | Uncertainty-Aware Deep MVPS · DiLiGenT-MV average | Chamfer-L1: 0.451 -> 0.414 | Helped |
| add the PS confidence variable (ablation) | Uncertainty-Aware Deep MVPS · DiLiGenT-MV average | Chamfer-L1: 0.433 -> 0.414 | Helped |
| add the MVS confidence variable (ablation) | Uncertainty-Aware Deep MVPS · DiLiGenT-MV average | Chamfer-L1: 0.586 -> 0.414 | Helped |
| use LCNet-predicted light sources instead of exact light calibration (ablation) | Uncertainty-Aware Deep MVPS · DiLiGenT-MV average | Chamfer-L1: 0.414 -> 0.431 | Hurt |
| add both PS and MVS confidence variables (ablation) | Uncertainty-Aware Deep MVPS · DiLiGenT-MV POT2 | Chamfer-L1: 0.481 -> 0.515 | Hurt |
| add both PS and MVS confidence variables (ablation) | Uncertainty-Aware Deep MVPS · DiLiGenT-MV COW | Chamfer-L1: 0.365 -> 0.329; 0.381 -> 0.329; 0.339 -> 0.329 | Mixed |
Closest papers by meaning
- Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (CVPR 2020 · similarity 0.90)
- MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction (CVPR 2024 · similarity 0.90)
- Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction (CVPR 2016 · similarity 0.90)
- Multi-View Stereo Representation Revist: Region-Aware MVSNet (CVPR 2023 · similarity 0.89)
- MVS2D: Efficient Multi-View Stereo via Attention-Driven 2D Convolutions (CVPR 2022 · similarity 0.89)
- A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding (NeurIPS 2024 · similarity 0.87)
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.