Research map / Point clouds / Registration and matching
Distinctiveness Oriented Positional Equilibrium for Point Cloud Registration
Taewon Min, Chonghyuk Song, Eunseok Kim, Inwook Shim
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 the DoPE module | DCP · ModelNet40 full+clean | MAE(R) degrees: 0.770573 -> 0.085278 | Improved |
| add the DoPE module | RPM-Net · ModelNet40 full+clean | MAE(R) degrees: 0.028 -> 0.0009 | Improved |
| add the DoPE module | DeepGMR · ModelNet40 full+clean | MAE(R) degrees: 0.0008 -> 0.0002 | Improved |
| add the DoPE module | DCP · ModelNet40 full+noisy | MAE(R) degrees: 4.528 -> 1.6240 | Improved |
| add the DoPE module | PRNet · ModelNet40 partial+clean | MAE(R) degrees: 1.454 -> 0.311634 | Improved |
| add the DoPE module | IDAM · ModelNet40 partial+noisy | MAE(R) degrees: 1.85 -> 0.423182 | Improved |
| add the DoPE module | DCP · ScanObjectNN | MAE(R) degrees: 5.749913 -> 1.731377 | Improved |
| add the DoPE module | DGR · 3DMatch | recall (%): 91.3% -> 96.6% | Improved |
| add local attention (ablation) | DCP · ModelNet40 full+noisy | MAE(R) degrees: 5.34 -> 4.74 | Improved |
| add non-local attention (ablation) | DCP · ModelNet40 full+noisy | MAE(R) degrees: 5.34 -> 4.45 | Improved |
| compute positional embeddings w.r.t. joint origin instead of individual origin with non-local attention (ablation) | DoPE** · ModelNet40 full+noisy | MAE(R) degrees: 3.86 -> 0.80 | Improved |
| compute positional embeddings w.r.t. joint origin instead of individual origin with local attention (ablation) | DoPE* · ModelNet40 full+noisy | MAE(R) degrees: 2.38 -> 1.04 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- RPMNet — RPM-Net: Robust Point Matching Using Learned Features (CVPR 2020) · better on 3 of 3 shared results
- PRNet — PRNet: Self-Supervised Learning for Partial-to-Partial Registration (NeurIPS 2019) · better on 3 of 3 shared results
- DeepGMR — DeepGMR: Learning Latent Gaussian Mixture Models for Registration (ECCV 2020) · better on 2 of 2 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
- OIF-PCR++: Point Cloud Registration via Progressive Distillation of Conditional Positional Encoding (TPAMI 2026 · similarity 0.90)
- Rethinking Point Cloud Registration as Masking and Reconstruction (ICCV 2023 · similarity 0.90)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (AAAI 2025 · similarity 0.90)
- PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations (AAAI 2024 · similarity 0.90)
- RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud Registration (ICML 2026 · similarity 0.90)
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · similarity 0.89)
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.
