Research map / Point clouds / Point cloud classification
Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| set the neighboring ratio to 5% instead of 10% (ablation) | 3D-GCN · ModelNet40 | Accuracy (%): 86.8 -> 63.3 | Hurt |
| set the neighboring ratio to 30% instead of 10% (ablation) | 3D-GCN · ModelNet40 | Accuracy (%): 86.8 -> 85.1 | Hurt |
| add learnable directional vectors to the kernel (ablation) | 3D-GCN · ModelNet10 | Accuracy(%): 89.5 -> 93.9 | Helped |
| replace fixed axis vectors with learnable directional vectors (ablation) | 3D-GCN · ModelNet10 | Accuracy(%): 92.2 -> 93.9 | Helped |
| use fixed axis vectors instead of no directional information (ablation) | 3D-GCN · ModelNet10 | Accuracy(%): 89.5 -> 92.2 | Helped |
Closest papers by meaning
- Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling (CVPR 2018 · similarity 0.91)
- Learning Localized Generative Models for 3D Point Clouds via Graph Convolution (ICLR 2019 · similarity 0.90)
- Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering (CVPR 2023 · similarity 0.90)
- Learning to Segment 3D Point Clouds in 2D Image Space (CVPR 2020 · similarity 0.90)
- PointCNN++: Performant Convolution on Native Points (CVPR 2026 · similarity 0.89)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · 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.