Research map / Point clouds / Point cloud classification
QPoint: End-to-End Lightweight Point Cloud Processing via Robust Quaternion Feature Learning
Zhiming Zhou, Yong He, Chaoxu Mu, Qiaoyun Wu, Ajmal Saeed Mian
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 quaternion rotation to QELP (ablation) | QPoint · ModelNet40 | OA: 93.6 -> 94.2 | Improved |
| add QELP module (ablation) | QPoint · ModelNet40 | OA: 93.0 -> 94.2 | Improved |
| add quaternion scoring to QGA (ablation) | QPoint · ModelNet40 | OA: 93.1 -> 94.2 | Improved |
| add QGA module (ablation) | QPoint · ModelNet40 | OA: 92.7 -> 94.2 | Improved |
| add QELP and QGA under Y-axis rotation (ablation) | QPoint · ModelNet40 rotation 90 deg | OA: 72.6/75.3 (no QGA/no QELP) -> 80.6 | Improved |
| use 4 QPoint blocks instead of 1 (ablation) | QPoint · ModelNet40 | OA: 93.5 -> 94.2 | Improved |
| increase QPB number from 4 to 8 (ablation) | QPoint · ModelNet40 | OA: 94.2 -> 93.9 | Hurt |
| increase tokens L from 128 to 384 (ablation) | QPoint · ModelNet40 | OA: 94.2 -> 93.5 | Hurt |
| increase tokens L from 32 to 128 (ablation) | QPoint · ModelNet40 | OA: 92.6 -> 94.2 | Improved |
| add voting at inference | QPoint · ModelNet40 | OA: 94.2 -> 94.7 | Improved |
| add voting at inference | QPoint · ScanObjectNN PB_T50_RS | OA: 90.7 -> 92.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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
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
- Interpretable Rotation-Equivariant Quaternion Neural Networks for 3D Point Cloud Processing (TPAMI 2024 · similarity 0.90)
- Quaternion Equivariant Capsule Networks for 3D Point Clouds (ECCV 2020 · similarity 0.89)
- Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning (AAAI 2026 · similarity 0.87)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.87)
- Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis (CVPR 2024 · similarity 0.87)
- CamPoint: Boosting Point Cloud Segmentation with Virtual Camera (CVPR 2025 · 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.
