Research map / Point clouds / Point cloud classification
Orderly Disorder in Point Cloud Domain
Morteza Ghahremani, Bernard Tiddeman, Yonghuai Liu, and Ardhendu Behera
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 |
|---|---|---|---|
| use Pattern-Net instead of DGCNN under noise N(0,0.05) | Pattern-Net · ModelNet40 with noise N(0,0.05) | accuracy %: 69.1 -> 92.4 | Improved |
| use Pattern-Net instead of DGCNN under noise N(0,0.1) | Pattern-Net · ModelNet40 with noise N(0,0.1) | accuracy %: 11.4 -> 84.2 | Improved |
| increase noise to N(0,0.15) for Pattern-Net (ablation) | Pattern-Net · ModelNet40 with noise | accuracy %: 84.2 -> 32.6 | Hurt |
| increase input points from 1k to 4k (ablation) | Pattern-Net · ModelNet40 classification | overall accuracy %: 92.9 -> 93.9 | Improved |
| increase input points from 1k to 2k (ablation) | Pattern-Net · ModelNet40 classification | overall accuracy %: 92.9 -> 93.6 | Improved |
| use Pattern-Net (2k) instead of DGCNN on clean data | Pattern-Net · ModelNet40 classification | overall accuracy %: 93.5 -> 93.6 | No clear effect |
| use Pattern-Net instead of RS-CNN for segmentation | Pattern-Net · ShapeNet part segmentation | average IoU %: 86.2 -> 86.4 | No clear effect |
| use Pattern-Net instead of DensePoint for parameter count | Pattern-Net · ModelNet40 classification | parameters: 670k -> 399k | Improved |
| increase neighbour parameter K up to 30 (ablation) | Pattern-Net · ModelNet40 classification | accuracy | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SO-Net — SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018) · better on 5 of 5 shared results
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 5 of 5 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
- PnP-3D: A Plug-and-Play for 3D Point Clouds (TPAMI 2021 · similarity 0.84)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.84)
- Fully-Convolutional Point Networks for Large-Scale Point Clouds (ECCV 2018 · similarity 0.84)
- Dataset Distillation of 3D Point Clouds via Distribution Matching (NeurIPS 2025 · similarity 0.83)
- A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification (ICML 2023 · similarity 0.83)
- Point Cloud Dataset Distillation (ICML 2025 · similarity 0.83)
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.
