Research map / 3D vision / Depth and stereo
Attention-Aware Multi-View Stereo
Keyang Luo, Tao Guan, Lili Ju, Yuesong Wang, Zhuo Chen, Yawei Luo
Check 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 |
|---|---|---|---|
| Use the modified feature extractor (ablation) | AttMVS · DTU validation set | MADE: 2.14 -> 1.96 | Improved |
| Add attention-enhanced matching confidence volume (ablation) | AttMVS · DTU validation set | MADE: 1.96 -> 1.91 | Improved |
| Add simple-RFM (ablation) | AttMVS · DTU validation set | MADE: 1.91 -> 1.89 | Improved |
| Add RFMs (ablation) | AttMVS · DTU validation set | MADE: 1.89 -> 1.82 | Improved |
| Train with the joint depth and inter-gradient loss (ablation) | AttMVS · DTU validation set | MADE: 1.82 -> 1.79 | Improved |
| Increase sampled depth planes from Z = 256 to Z = 384 | AttMVS · DTU evaluation scenes | overall: 0.403 -> 0.368 | Improved |
| Add depth-map refinement | AttMVS (Z = 384) · DTU evaluation scenes | overall: 0.368 -> 0.356 | Improved |
| Use AttMVS rather than the strongest reported baseline | Tanks & Temples intermediate · Tanks & Temples intermediate | mean F-score: 59.03 -> 60.05 | Improved |
| Use AttMVS rather than the strongest reported baseline | Tanks & Temples advanced · Tanks & Temples advanced | mean F-score: 37.34 -> 31.93 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- P-MVSNet — P-MVSNet: Learning Patch-Wise Matching Confidence Aggregation for Multi-View Stereo (ICCV 2019) · better on 1 of 1 shared result
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
- A Confidence-Based Iterative Solver of Depths and Surface Normals for Deep Multi-View Stereo (ICCV 2021 · similarity 0.89)
- A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding (NeurIPS 2024 · similarity 0.89)
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (CVPR 2020 · similarity 0.89)
- Generalized Binary Search Network for Highly-Efficient Multi-View Stereo (CVPR 2022 · similarity 0.89)
- MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo (ICLR 2024 · similarity 0.88)
- RRT-MVS: Recurrent Regularization Transformer for Multi-View Stereo (AAAI 2025 · similarity 0.88)
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.
