Research map / Point clouds / Point cloud classification
A-CNN: Annularly Convolutional Neural Networks on Point Clouds
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 |
|---|---|---|---|
| Use A-CNN instead of PointNet++ | Point cloud classification · ModelNet40 | OA: 91.9 -> 92.6 | Helped |
| Use A-CNN instead of Point2Sequence | Point cloud classification · ModelNet40 | AAC: 90.4 -> 90.3 | Hurt |
| Use A-CNN instead of PointGrid | Point cloud part segmentation with XYZ input · ShapeNet-part | mean IoU: 86.4 -> 85.9 | Hurt |
| Add normals as input features | A-CNN · ShapeNet-part | mean IoU: 85.9 -> 86.1 | Helped |
| Use A-CNN instead of PointCNN | Large-scale semantic segmentation · S3DIS | OA: 88.1 -> 87.3 | Hurt |
| Use A-CNN instead of PointCNN | Large-scale semantic segmentation · ScanNet | OA: 85.1 -> 85.4 | Helped |
| Add non-overlapping ring neighborhoods in place of overlapping multi-scale regions (ablation) | PointNet++ · ModelNet40 | AAC: 86.5 -> 87.3 | Helped |
| Add non-overlapping ring neighborhoods instead of overlapping ball query (ablation) | A-CNN · ModelNet40 | AAC: 89.2 -> 90.3 | Helped |
| Add non-overlapping ring neighborhoods instead of overlapping ball query (ablation) | A-CNN · ModelNet40 | OA: 91.7 -> 92.6 | Helped |
| Add annular convolutions (ablation) | A-CNN · ModelNet40 | AAC: 89.2 -> 90.3 | Helped |
| Add annular convolutions (ablation) | A-CNN · ModelNet40 | OA: 91.8 -> 92.6 | Helped |
| Add neighbor ordering (ablation) | A-CNN · ModelNet40 | AAC: 89.6 -> 90.3 | Helped |
Closest papers by meaning
- Pointwise Convolutional Neural Networks (CVPR 2018 · similarity 0.91)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017 · similarity 0.91)
- PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019 · similarity 0.90)
- Shape-Oriented Convolution Neural Network for Point Cloud Analysis (AAAI 2020 · similarity 0.89)
- Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN (CVPR 2019 · similarity 0.89)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · 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.