Research map / Point clouds / Point cloud classification
Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning
Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Shengfeng He
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 |
|---|---|---|---|
| apply intricate orientation learning (DG) vs no adaptation | source-trained classifier · PointDA orientation-aware (micro Acc) | accuracy: 42.5 -> 53.3 | Improved |
| use intricate orientation learning instead of Metasets | 3D DG methods · PointDA orientation-aware (micro Acc) | accuracy: 37.4 -> 53.3 | Improved |
| apply intricate orientation mining on z-axis only | source-trained classifier · PointDA aligned | accuracy: 62.2 -> 67.5 | Improved |
| use intricate orientation learning instead of PDG | 3D DG methods · PointDA aligned | accuracy: 57.9 -> 46.0 on M->S*; 66.3 -> 70.3 on S*->S | Mixed |
| vary lambda_oc (ablation) | orientation consistency loss weight · PointDA M->S | accuracy | No clear effect |
| increase lambda_ms (ablation) | marginal separation loss weight · PointDA M->S | accuracy | Hurt |
| add diversified intricate orientation set update | training pipeline · PointDA | training time per batch: 567 -> 2114 | Hurt |
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.
- Metasets — MetaSets: Meta-Learning on Point Sets for Generalizable Representations (CVPR 2021) · better on 2 of 3 shared results
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
- Upright-Net: Learning Upright Orientation for 3D Point Cloud (CVPR 2022 · similarity 0.88)
- Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning (AAAI 2026 · similarity 0.88)
- Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning (ICML 2023 · similarity 0.88)
- Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis (NeurIPS 2024 · similarity 0.88)
- Learning Generalizable Part-based Feature Representation for 3D Point Clouds (NeurIPS 2022 · similarity 0.87)
- Dataset Distillation of 3D Point Clouds via Distribution Matching (NeurIPS 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.
