Research map / Point clouds / Point cloud classification
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis
Check 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 |
|---|---|---|---|
| use a rigorously rotation-invariant representation and ClusterNet rather than Spherical CNN | ModelNet40 classification · ModelNet40 SO(3)/SO(3) | accuracy: 86.9 -> 87.1 | Helped |
| use a rigorously rotation-invariant representation and ClusterNet rather than DGCNN | ModelNet40 classification · ModelNet40 z/SO(3) | accuracy: 20.6 -> 87.1 | Helped |
| use a rigorously rotation-invariant representation and ClusterNet rather than DGCNN | ModelNet40 classification · ModelNet40 SO(3)/SO(3)* | accuracy: 82.0 -> 87.1 | Helped |
| use ClusterNet rather than PointNet to process the RRI representation (ablation) | RRI point-cloud classifier · ModelNet40 | accuracy: 85.9 -> 87.1 | Helped |
| use ClusterNet rather than DGCNN to process the RRI representation (ablation) | RRI point-cloud classifier · ModelNet40 | accuracy: 86.4 -> 87.1 | Helped |
| add hierarchical cluster level 8 to the (32, 1) configuration (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 86.8 -> 87.1 | Helped |
| add hierarchical cluster level 32 to the (8, 1) configuration (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 86.6 -> 87.1 | Helped |
| set RRI neighborhood size K to 40 rather than 80 (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 87.1 -> 85.6 | Hurt |
| set RRI neighborhood size K to 50 rather than 80 (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 87.1 -> 86.4 | Hurt |
| set RRI neighborhood size K to 60 rather than 80 (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 87.1 -> 86.8 | Hurt |
| set RRI neighborhood size K to 70 rather than 80 (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 87.1 -> 87.0 | No clear effect |
| set RRI neighborhood size K to 90 rather than 80 (ablation) | RRI+ClusterNet · ModelNet40 | accuracy: 87.1 -> 87.1 | No clear effect |
Closest papers by meaning
- Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud (NeurIPS 2020 · similarity 0.91)
- Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution (AAAI 2020 · similarity 0.89)
- CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame (AAAI 2023 · similarity 0.88)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.87)
- RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning (AAAI 2025 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 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.