Research map / Point clouds / Registration and matching
OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration
Hao Xu, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng
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 mask prediction module without mask supervision (ablation) | OMNet baseline · unseen shapes with noise (TS) | Error(R): 5.250 -> 5.550 | Hurt |
| add mask prediction loss to mask module (ablation) | OMNet · unseen shapes with noise (TS) | Error(R): 5.550 -> 2.681 | Improved |
| add fusion layers before regression (ablation) | OMNet · unseen shapes with noise (TS) | Error(R): 2.681 -> 1.722 | Improved |
| add connection between mask prediction and regression modules (ablation) | OMNet · unseen shapes with noise (TS) | Error(R): 1.722 -> 1.490 | Improved |
| use only top-k points by mask instead of soft mask (k=500) (ablation) | OMNet · unseen shapes with noise (TS) | Error(R): 1.490 -> 2.255 | Hurt |
| reduce top-k from 500 to 100 (ablation) | OMNet · unseen shapes with noise (TS) | Error(R): 2.255 -> 2.458 | Hurt |
| increase mask loss weight lambda from 0.1 to 2.0 (ablation) | OMNet · unseen shapes with noise (TS) | Error(R): 2.038 -> 1.721 | Improved |
| train and test on twice-sampled data instead of once-sampled (unseen shapes) (ablation) | OMNet · ModelNet40 unseen shapes | Error(R): 0.639 -> 0.991 | Hurt |
| compare OMNet with PRNet on unseen shapes TS | OMNet versus PRNet · ModelNet40 unseen shapes (TS) | Error(R): 4.223 -> 0.991 | Improved |
| compare OMNet with RPMNet under RPMNet partial manner | OMNet versus RPMNet · ModelNet40 unseen categories with noise | Error(R): 4.913 -> 3.834 | Improved |
| train on once-sampled data (OS) instead of twice-sampled (TS) for DCP on noise (ablation) | DCP · ModelNet40 Gaussian noise | Error(R): 6.653 -> 6.024 | Mixed |
Later papers that compared with this method
2 later accepted papers report Omnet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Cross3DReg: A Real-world Cross-source Point Cloud Registration Benchmark (IJCV 2026 · better on 1 of 1 shared result)
- FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration (AAAI 2022 · better on 6 of 7 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PRNet — PRNet: Self-Supervised Learning for Partial-to-Partial Registration (NeurIPS 2019) · better on 6 of 6 shared results
- RPMNet — RPM-Net: Robust Point Matching Using Learned Features (CVPR 2020) · 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
- Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration (ECCV 2020 · similarity 0.91)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (NeurIPS 2024 · similarity 0.89)
- Deep Confidence Guided Distance for 3D Partial Shape Registration (AAAI 2022 · similarity 0.89)
- Implicit Correspondence Learning for Image-to-Point Cloud Registration (CVPR 2025 · similarity 0.88)
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · similarity 0.88)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (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.
