Research map / Point clouds / Registration and matching
2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Images and Point Clouds
Minhao Li, Zheng Qin, Zhirui Gao, Renjiao Yi, Chenyang Zhu, Yulan Guo, Kai Xu
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 coarse-to-fine patch matching instead of matching random keypoints (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Registration Recall: 34.6 -> 56.4 | Improved |
| add self-attention in feature refinement (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Registration Recall: 44.0 -> 56.4 | Improved |
| add cross-attention in feature refinement (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Registration Recall: 47.7 -> 56.4 | Improved |
| add attention modules overall (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Inlier Ratio: 23.1 -> 32.4 | Improved |
| use 3-level multi-scale patch pyramid instead of a single resolution (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Registration Recall: 36.9 -> 56.4 (vs 24x32 only) | Improved |
| use the 6x8 coarse level in addition to finer levels (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Patch Inlier Ratio: PIR 49.8 (12x16+6x8) vs 48.5 (full) | Mixed |
| remove self-attention (ablation) | 2D3D-MATR · RGB-D Scenes V2 | Feature Matching Recall: 90.8 -> 91.8 | No clear effect |
| 2D3D-MATR instead of P2-Net on RGB-D Scenes V2 | P2-Net · RGB-D Scenes V2 | Registration Recall: 38.4 -> 56.4 | Improved |
| 2D3D-MATR instead of P2-Net on 7Scenes | P2-Net · 7Scenes | Registration Recall: 65.7 -> 75.8 | Improved |
| predict overlap scores for keypoint sampling (Predator-2D3D) on 7Scenes | Predator-2D3D · 7Scenes | Registration Recall: 61.4 -> 48.5 (vs FCGF-2D3D) | Hurt |
Later papers that compared with this method
8 later accepted papers report 2D3D-MATR as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.
- FS-I2P: A Hierarchical Focus–Sweep Registration Network with Dynamically Allocated Depth (ICML 2026 · better on 7 of 7 shared results)
- Adaptive Agent Selection and Interaction Network for Image-to-Point Cloud Registration (AAAI 2026 · better on 7 of 7 shared results)
- Rethinking 2D-3D Registration: A Novel Network for High-Value Zone Selection and Representation Consistency Alignment (CVPR 2026 · better on 4 of 6 shared results)
- UniCorrn: Unified Correspondence Transformer Across 2D and 3D (CVPR 2026 · better on 1 of 1 shared result)
- Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior (ICCV 2025 · better on 9 of 9 shared results)
- Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment (AAAI 2025 · better on 6 of 6 shared results)
- CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection (ICCV 2025 · better on 6 of 6 shared results)
- GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning (CVPR 2025 · better on 4 of 4 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
- Geometric Transformer for Fast and Robust Point Cloud Registration (CVPR 2022 · similarity 0.90)
- Rethinking 2D-3D Registration: A Novel Network for High-Value Zone Selection and Representation Consistency Alignment (CVPR 2026 · similarity 0.90)
- Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model (CVPR 2025 · similarity 0.89)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.89)
- Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework (AAAI 2025 · similarity 0.88)
- Generative Point Cloud Registration (ICML 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.
