Research map / Point clouds / Point cloud classification
PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification
Xinxing Yu, Liying Yang, Hao Mo, Hui Ma, Fang Kai, Ajian Liu, Yanyan Liang
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 HST (hyperbolic semantic transformation) (ablation) | CamPoint baseline · ScanObjectNN | OA: 92.1 -> 92.2 | Improved |
| add HST (ablation) | CamPoint baseline · S3DIS Area5 | mIoU: 83.3 -> 84.1 | Improved |
| add PCP (curvature-adaptive perception) (ablation) | CamPoint baseline · ScanObjectNN | OA: 92.1 -> 92.5 | Improved |
| add PCP (ablation) | CamPoint baseline · S3DIS Area5 | mIoU: 83.3 -> 84.8 | Improved |
| add HST on top of PCP (ablation) | PointCHR · ScanObjectNN | OA: 92.5 -> 92.8 | Improved |
| add HST on top of PCP (ablation) | PointCHR · S3DIS Area5 | mIoU: 84.8 -> 86.0 | Improved |
| plug CHR into PointMLP | PointMLP · ScanObjectNN | OA: 85.4 -> 86.2 | Improved |
| plug CHR into DeLA | DeLA · ScanObjectNN | OA: 90.4 -> 90.9 | Improved |
| plug CHR into DeLA | DeLA · S3DIS | mIoU: 73.2 -> 75.3 | Improved |
| plug CHR into PointNext-s | PointNext-s · S3DIS | mIoU: 63.4 -> 65.3 | Improved |
| use PointCHR instead of baseline in highest-curvature bin | CamPoint · S3DIS curvature bin [0.15, 0.20] | mIoU: 66.22 -> 76.62 | Improved |
| use PointCHR instead of baseline in lowest-curvature bin | CamPoint · S3DIS curvature bin [0.00, 0.05) | mIoU: 84.39 -> 86.59 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- CamPoint — CamPoint: Boosting Point Cloud Segmentation with Virtual Camera (CVPR 2025) · better on 5 of 5 shared results
- Sonata — Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025) · better on 2 of 2 shared results
- LinNet — LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024) · 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
- Dual Manifold Regularization Steered Robust Representation Learning for Point Cloud Analysis (AAAI 2025 · similarity 0.89)
- Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion (AAAI 2025 · similarity 0.88)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.87)
- Hyperbolic-Constraint Point Cloud Reconstruction from Single RGB-D Images (AAAI 2025 · similarity 0.87)
- Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation (CVPR 2025 · similarity 0.87)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.87)
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.
