Research map / Point clouds / Point cloud classification
Adaptive Graph Convolution for Point Cloud Analysis
Haoran Zhou, Yidan Feng, Mingsheng Fang, Mingqiang Wei, Jing Qin, Tong Lu
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 adaptive kernels instead of standard graph convolution (ablation) | AdaptConv · ShapeNetPart | mcIoU: 81.9 -> 83.4 | Improved |
| use adaptive kernels instead of standard graph convolution (ablation) | AdaptConv · ShapeNetPart | mIoU: 85.5 -> 86.4 | Improved |
| use adaptive kernels instead of point attention weights (ablation) | AdaptConv · ShapeNetPart | mIoU: 83.3 -> 86.4 | Improved |
| use adaptive kernels instead of channel attention (ablation) | AdaptConv · ShapeNetPart | mIoU: 83.0 -> 86.4 | Improved |
| convolve kernel with xyz instead of previous-layer features (ablation) | AdaptConv · ShapeNetPart | mcIoU: 82.2 -> 83.4 | Improved |
| use xyz inputs instead of normals only (ablation) | AdaptConv · ShapeNetPart | mcIoU: 83.2 -> 83.4 | Improved |
| use xyz inputs instead of xyz plus normals (ablation) | AdaptConv · ShapeNetPart | mIoU: 86.1 -> 86.4 | No clear effect |
| increase neighborhood size k from 5 to 20 (ablation) | AdaptConv · ModelNet40 | OA: 92.8 -> 93.4 | Improved |
| increase neighborhood size k from 20 to 40 (ablation) | AdaptConv · ModelNet40 | OA: 93.4 -> 93.0 | Hurt |
| increase neighborhood size k from 10 to 20 (ablation) | AdaptConv · ModelNet40 | OA: 93.2 -> 93.4 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- PointASNL — PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling (CVPR 2020) · better on 5 of 5 shared results
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 3 of 3 shared results
- SO-Net — SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018) · better on 0 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
- AGConv: Adaptive Graph Convolution on 3D Point Clouds (TPAMI 2023 · similarity 0.94)
- PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019 · similarity 0.90)
- Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis (CVPR 2020 · similarity 0.89)
- Learning of 3D Graph Convolution Networks for Point Cloud Analysis (TPAMI 2021 · similarity 0.89)
- PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label (ICCV 2023 · similarity 0.89)
- PAConv: Position Adaptive Convolution With Dynamic Kernel Assembling on Point Clouds (CVPR 2021 · 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.
