Research map / 3D vision / Depth and stereo
PatchMatch-RL: Deep MVS With Pixelwise Depth, Normal, and Visibility
Jae Yong Lee, Joseph DeGol, Chuhang Zou, Derek Hoiem
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 normal estimation with dilated patch kernels (ablation) | PatchMatch-RL · ETH3D train 2cm | F1: 54.0 -> 67.8 | Improved |
| add normal estimation with dilated patch kernels (ablation) | PatchMatch-RL · ETH3D train 5cm | F1: 75.1 -> 83.3 | Improved |
| add pixelwise view selection (ablation) | PatchMatch-RL · ETH3D train 2cm | F1: 64.1 -> 67.8 | Improved |
| add pixelwise view selection (ablation) | PatchMatch-RL · ETH3D train 5cm | F1: 79.8 -> 83.3 | Improved |
| add recurrent cost regularization (ablation) | PatchMatch-RL · ETH3D train 2cm | F1: 66.7 -> 67.8 | Improved |
| add recurrent cost regularization (ablation) | PatchMatch-RL · ETH3D train 5cm | F1: 82.6 -> 83.3 | Improved |
| replace soft-argmax candidates with RL-trained argmax sampling (ablation) | PatchMatch-RL · ETH3D | F1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PatchmatchNet — PatchmatchNet: Learned Multi-View Patchmatch Stereo (CVPR 2021) · better on 3 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PatchmatchNet: Learned Multi-View Patchmatch Stereo (CVPR 2021 · similarity 0.93)
- DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo (AAAI 2025 · similarity 0.89)
- Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo (AAAI 2024 · similarity 0.88)
- Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization (AAAI 2025 · similarity 0.88)
- MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo (ICLR 2024 · similarity 0.87)
- MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo (AAAI 2025 · 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.
