Research map / Point clouds / Point cloud classification
PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Pre-train with PointClustering rather than Point-MAE | PointViT · ModelNet40 | top-1 accuracy: 93.8 -> 94.5 | Helped |
| Pre-train with PointClustering rather than MaskSurf | PointViT · ScanObjectNN PB-T50-RS | top-1 accuracy: 85.8 -> 87.3 | Helped |
| Pre-train with PointClustering rather than Point-MAE | PointViT · ShapeNetPart | instance mIoU: 86.1 -> 86.7 | Helped |
| Pre-train with PointClustering rather than scratch training | PointViT · PartNet | instance mIoU: 45.8 -> 50.1 | Helped |
| Pre-train with PointClustering rather than CSC | SR-UNet · S3DIS | mIoU: 72.2 -> 73.2 | Helped |
| Pre-train with PointClustering rather than PointContrast | SR-UNet · ScanNetV2 | mIoU: 74.1 -> 75.5 | Helped |
| Add point-level invariance learning (ablation) | PointClustering on PointNet++ · ModelNet40 | top-1 accuracy: 91.5 -> 93.0 | Helped |
| Add point-level invariance learning (ablation) | PointClustering on PointNet++ · ScanObjectNN | top-1 accuracy: 80.1 -> 82.6 | Helped |
| Add instance-level invariance learning (ablation) | PointClustering on PointNet++ · ModelNet40 | top-1 accuracy: 91.5 -> 93.4 | Helped |
| Add instance-level invariance learning (ablation) | PointClustering on PointNet++ · ScanObjectNN | top-1 accuracy: 80.1 -> 83.1 | Helped |
| Add point-level and instance-level invariance learning together (ablation) | PointClustering on PointNet++ · ModelNet40 | top-1 accuracy: 91.5 -> 94.1 | Helped |
| Add point-level and instance-level invariance learning together (ablation) | PointClustering on PointNet++ · ScanObjectNN | top-1 accuracy: 80.1 -> 84.5 | Helped |
Closest papers by meaning
- Masked Clustering Prediction for Unsupervised Point Cloud Pre-training (AAAI 2026 · similarity 0.88)
- Point Cloud Pre-training with Diffusion Models (CVPR 2024 · similarity 0.86)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 2024 · similarity 0.86)
- RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning (AAAI 2025 · similarity 0.86)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.86)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.86)
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.