Research map / Point clouds / Point cloud classification
Shaping Without Tearing: Controllable Diffeomorphic Deformations for Topology-Preserving 3D Point Cloud Augmentation
Jian Bi, Qianliang Wu, Jianjun Qian, Lei Luo, Jian Yang
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 diffeomorphic deformation (ablation) | ManiPoint on DGCNN · ScanObjectNN OBJ-ONLY | OA: 88.812 -> 90.478 | Improved |
| add average deformation rate control (ablation) | ManiPoint on DGCNN · ScanObjectNN OBJ-ONLY | OA: 88.643 -> 90.478 | Improved |
| use a single deformation function instead of multiple (ablation) | ManiPoint on DGCNN · ScanObjectNN OBJ-ONLY | OA: 89.673 -> 90.478 | Improved |
| control deformation rate in PointWOLF (ablation) | PointWOLF on DGCNN · ScanObjectNN OBJ-ONLY | OA: 87.653 -> 88.796 | Improved |
| add ManiPoint augmentation | Point-MAE · ModelNet40 few-shot | accuracy: 97.8 -> 97.9 (5-way 20-shot) | No clear effect |
| add ManiPoint augmentation | MinkNet · SemanticKITTI | mIoU: 55.9 -> 68.1 | Improved |
| add ManiPoint augmentation | PointNet++ · ModelNet40 | OA: 90.7 -> 93.5 | Improved |
| add ManiPoint augmentation | DGCNN · ScanObjectNN PB-T50-RS | OA: 77.3 -> 84.7 | Improved |
| add ManiPoint augmentation | DeLA · ScanObjectNN PB-T50-RS | Top-1 error: 9.6 -> 9.3 | Improved |
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.
- Point-M2AE — Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training (NeurIPS 2022) · better on 1 of 1 shared result
- +SageMix — SageMix: Saliency-Guided Mixup for Point Clouds (NeurIPS 2022) · 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
- Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation (ICML 2025 · similarity 0.92)
- SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation (CVPR 2024 · similarity 0.88)
- IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment (CVPR 2022 · similarity 0.88)
- 3DeformRS: Certifying Spatial Deformations on Point Clouds (CVPR 2022 · similarity 0.88)
- Topology-aware Feature Propagation for Unsupervised Non-rigid Point Cloud Correspondence (CVPR 2026 · similarity 0.88)
- GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model (ICML 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.
