Research map / 3D vision / Depth and stereo
TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo
Andrea Romanoni, Matteo Matteucci
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 |
|---|---|---|---|
| add texture weighting (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=2cm) | F1-score (%): 63.08 -> 77.69 | Improved |
| add coarse superpixel hypotheses (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=2cm) | F1-score (%): 72.54 -> 77.69 | Improved |
| add fine superpixel hypotheses (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=2cm) | F1-score (%): 72.26 -> 77.69 | Improved |
| add depth refinement (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=2cm) | F1-score (%): 71.84 -> 77.69 | Improved |
| add depth refinement (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=2cm) | accuracy (%): 83.32 -> 85.88 | Improved |
| add texture weighting (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=2cm) | completeness (%): 52.57 -> 71.45 | Improved |
| add texture weighting (ablation) | TAPA-MVS · ETH3D training high-res (13 seqs, tau=1cm) | F1-score (%): 44.58 -> 60.85 | Improved |
| add textureness-aware hypotheses and refinement to COLMAP | COLMAP · ETH3D training high-res (13 seqs, tau=2cm) | completeness (%): 55.13 -> 71.45 | Improved |
| add textureness-aware hypotheses and refinement to COLMAP | COLMAP · ETH3D training high-res (13 seqs, tau=2cm) | accuracy (%): 91.85 -> 85.88 | Hurt |
| add textureness-aware hypotheses and refinement to COLMAP | COLMAP · ETH3D training high-res (13 seqs, tau=2cm) | F1-score (%): 67.66 -> 77.69 | Improved |
Closest papers by meaning
- Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization (AAAI 2025 · similarity 0.90)
- DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo (AAAI 2025 · similarity 0.90)
- SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization (AAAI 2024 · similarity 0.89)
- PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.88)
- MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo (AAAI 2025 · similarity 0.88)
- Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo (AAAI 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.
