Research map / Point clouds / Point cloud classification
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
Tiange Xiang, Chaoyi Zhang, Yang Song, Jianhui Yu, Weidong Cai
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 curve grouping and aggregation (ablation) | CurveNet · ShapeNetPart | mean IoU: 85.9 -> 86.6 | Improved |
| add curve grouping and aggregation (ablation) | CurveNet · ModelNet40 normal estimation | avg cosine-distance error (lower better): 0.16 -> 0.11 | Improved |
| add curve aggregation operator instead of vanilla non-local (ablation) | CurveNet · ModelNet40 | accuracy: 93.1 -> 93.8 | Improved |
| add dynamic momentum (ablation) | CurveNet · ModelNet40 | accuracy: 93.3 -> 93.8 | Improved |
| add crossover suppression (ablation) | CurveNet · ModelNet40 | accuracy: 93.4 -> 93.8 | Improved |
| add LPFA block in presence of curves (ablation) | CurveNet · ModelNet40 | accuracy: 93.4 -> 93.8 | Improved |
| add LPFA without curves (ablation) | baseline · ModelNet40 | accuracy: 93.1 -> 93.3 | No clear effect |
| aggregate curves at shallow layers (groups 1/2) rather than deep layers (3/4) (ablation) | CurveNet · ModelNet40 | accuracy | Improved |
| increase curve length beyond 50 at fixed total points (ablation) | CurveNet · ModelNet40 | accuracy | 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.
- PointASNL — PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling (CVPR 2020) · 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
- Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (ICML 2021 · similarity 0.89)
- CurveCloudNet: Processing Point Clouds with 1D Structure (CVPR 2024 · similarity 0.89)
- Clustering based Point Cloud Representation Learning for 3D Analysis (ICCV 2023 · similarity 0.88)
- BoW Pooling: A Plug-and-Play Unit for Feature Aggregation of Point Clouds (AAAI 2021 · similarity 0.88)
- Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis (AAAI 2026 · similarity 0.88)
- Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework (ICLR 2022 · similarity 0.88)
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.
