Research map / 3D vision / Depth and stereo
Planar Prior Assisted PatchMatch Multi-View Stereo
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 |
|---|---|---|---|
| add planar-prior-assisted matching cost and geometric consistency (ablation) | PatchMatch MVS (ACMP) · ETH3D high-resolution training datasets, average | pixels with absolute depth error below 2 cm (%): 72.9 -> 81.9 | Helped |
| add planar-prior-assisted matching cost and geometric consistency (ablation) | PatchMatch MVS (ACMP) · ETH3D high-resolution training datasets, average | pixels with absolute depth error below 10 cm (%): 85.1 -> 90.6 | Helped |
| add geometric consistency (ablation) | ACMP without geometric consistency · ETH3D high-resolution training datasets, average | pixels with absolute depth error below 2 cm (%): 72.9 -> 81.9 | Helped |
| add geometric consistency (ablation) | ACMP without geometric consistency · ETH3D high-resolution training datasets, average | pixels with absolute depth error below 10 cm (%): 85.1 -> 90.6 | Helped |
| add geometric consistency (ablation) | ACMP without geometric consistency · ETH3D high-resolution test datasets (all, 2 cm) | F1 score (%) | Helped |
| use planar-prior-assisted matching with geometric consistency instead of ACMM | ETH3D MVS · ETH3D high-resolution test datasets (all, 2 cm) | F1 score (%): 80.78 -> 81.51 | Helped |
| use planar-prior-assisted matching with geometric consistency instead of COLMAP | ETH3D MVS · ETH3D high-resolution test datasets (all, 2 cm) | accuracy (%): 91.97 -> 90.54 | Hurt |
| use planar-prior-assisted matching with geometric consistency instead of openMVS | ETH3D MVS · ETH3D high-resolution test datasets (all, 2 cm) | completeness (%): 78.54 -> 75.58 | Hurt |
| use planar-prior-assisted matching with geometric consistency instead of ACMM | ETH3D MVS · ETH3D high-resolution training datasets, average | pixels with absolute depth error below 10 cm (%): 90.7 -> 90.6 | No clear effect |
Closest papers by meaning
- Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization (AAAI 2025 · similarity 0.92)
- PatchmatchNet: Learned Multi-View Patchmatch Stereo (CVPR 2021 · similarity 0.90)
- DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo (AAAI 2025 · similarity 0.89)
- MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo (AAAI 2025 · similarity 0.88)
- SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization (AAAI 2024 · similarity 0.87)
- Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo (AAAI 2024 · similarity 0.86)
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.