Research map / 3D vision / Depth and stereo
Adaptive Patch Deformation for Textureless-Resilient 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 |
|---|---|---|---|
| Replace fixed-window matching for unreliable pixels with adaptive deformable patches anchored by reliable pixels | PatchMatch-based MVS (APD-MVS) · ETH3D test | F1 | Helped |
| Use weighted aggregation of center-patch and anchor-pixel costs rather than mixed aggregation over the combined patch (ablation) | APD-MVS · ETH3D, 2cm | F1: 83.73 -> 86.84 | Helped |
| Use weighted aggregation of center-patch and anchor-pixel costs rather than mixed aggregation over the combined patch (ablation) | APD-MVS · ETH3D, 10cm | F1: 95.68 -> 97.12 | Helped |
| Evaluate reliability using matching-cost profile geometry instead of color standard deviation (ablation) | APD-MVS · ETH3D, 2cm | F1: 81.57 -> 86.84 | Helped |
| Evaluate reliability using matching-cost profile geometry instead of a matching-cost threshold (ablation) | APD-MVS · ETH3D, 2cm | F1: 76.71 -> 86.84 | Helped |
| Evaluate reliability using matching-cost profile geometry instead of color standard deviation (ablation) | APD-MVS · ETH3D, 10cm | F1: 94.46 -> 97.12 | Helped |
| Evaluate reliability using matching-cost profile geometry instead of a matching-cost threshold (ablation) | APD-MVS · ETH3D, 10cm | F1: 91.66 -> 97.12 | Helped |
Closest papers by meaning
- MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo (AAAI 2025 · similarity 0.89)
- DVP-MVS: Synergize Depth-Edge and Visibility Prior for 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 0.88)
- Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization (AAAI 2025 · similarity 0.88)
- Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo (AAAI 2024 · similarity 0.87)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · 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.