Research map / Point clouds / Point cloud classification
Dynamic Points Agglomeration for Hierarchical Point Sets Learning
Jinxian Liu, Bingbing Ni, Caiyuan Li, Jiancheng Yang, Qi Tian
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 parameter sharing with part division (8-4-1 instead of 1-1-1) (ablation) | Dynamic points agglomeration · ModelNet40 | instance accuracy (%): 90.9 -> 91.9 | Improved |
| merge parts gradually (4-2-1 instead of constant 8-8-8) (ablation) | Dynamic points agglomeration · ModelNet40 | instance accuracy (%): 91.2 -> 91.7 | Improved |
| add T-Net to the model (ablation) | Dynamic points agglomeration · ModelNet40 | instance accuracy (%): 91.4 -> 91.9 | Improved |
| divide input along x-axis instead of randomly (ablation) | Dynamic points agglomeration · ModelNet40 | instance accuracy (%): 90.9 -> 91.9 | Improved |
| choose z-axis instead of x-axis for division (ablation) | Dynamic points agglomeration · ModelNet40 | instance accuracy (%): 91.9 -> 91.8 | No clear effect |
| choose y-axis instead of x-axis for division (ablation) | Dynamic points agglomeration · ModelNet40 | instance accuracy (%): 91.9 -> 91.6 | No clear effect |
| add T-Net to the model (cost) (ablation) | Dynamic points agglomeration · ModelNet40 | inference time (ms): 18.4 -> 36.6 | Hurt |
| use learned agglomeration versus PointNet++ under Gaussian noise | Dynamic points agglomeration · ModelNet40 noise robustness | accuracy | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 3 of 7 shared results
- SO-Net — SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018) · better on 4 of 4 shared results
- SGPN — SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation (CVPR 2018) · 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
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (NeurIPS 2017 · similarity 0.87)
- DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning (AAAI 2024 · similarity 0.86)
- Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling (CVPR 2018 · similarity 0.86)
- AGConv: Adaptive Graph Convolution on 3D Point Clouds (TPAMI 2023 · similarity 0.86)
- PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning (AAAI 2025 · similarity 0.85)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.84)
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.
