Research map / Point clouds / Point cloud classification
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
Yifan Xu, Tianqi Fan, Mingye Xu, Long Zeng, Yu Qiao
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 top-2 pooling instead of max-pooling (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 92.0 -> 92.4 | Improved |
| use top-2 pooling instead of max-pooling (ablation) | SpiderCNN 3-layer · ModelNet40 | accuracy (%): 90.4 -> 91.5 | Improved |
| use step times Taylor filter instead of MLP(16, 1) filter (ablation) | SpiderCNN 3-layer · ModelNet40 | accuracy (%): 71.3 -> 91.5 | Improved |
| use step times Taylor filter instead of MLP(16, 32, 1) filter (ablation) | SpiderCNN 3-layer · ModelNet40 | accuracy (%): 72.8 -> 91.5 | Improved |
| use order-3 Taylor instead of MLP(10, 5, 3) in the Taylor slot (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 91.6 -> 92.4 | Improved |
| use order-3 Taylor instead of MLP(6, 5, 3) (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 91.1 -> 92.4 | Improved |
| use order-3 Taylor instead of order-2 Taylor (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 91.9 -> 92.4 | Improved |
| use order-3 Taylor instead of linear Taylor (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 91.6 -> 92.4 | Improved |
| use order-3 Taylor instead of trilinear form f_wT (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 91.9 -> 92.4 | Improved |
| add normal vectors to the 1,024 input points (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 90.5 -> 92.4 | Improved |
| estimate normals from the 1,024 points by orthogonal distance regression (ablation) | SpiderCNN 4-layer · ModelNet40 | accuracy (%): 90.5 -> 91.8 | Improved |
| concatenate PointNet global features with 3-layer SpiderCNN features (ablation) | SpiderCNN 3-layer · ModelNet40 | accuracy (%): 91.5 -> 92.2 | Improved |
Later papers that compared with this method
9 later accepted papers report SpiderCNN as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- AGConv: Adaptive Graph Convolution on 3D Point Clouds (TPAMI 2023 · better on 1 of 1 shared result)
- Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis (TPAMI 2023 · better on 1 of 1 shared result)
- PRIN/SPRIN: On Extracting Point-Wise Rotation Invariant Features (TPAMI 2021 · better on 0 of 1 shared result)
- Geometry Sharing Network for 3D Point Cloud Classification and Segmentation (AAAI 2020 · better on 1 of 2 shared results)
- Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution (AAAI 2020 · better on 0 of 2 shared results)
- PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019 · better on 2 of 2 shared results)
- Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data (ICCV 2019 · better on 2 of 2 shared results)
- Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition (CVPR 2019 · better on 1 of 1 shared result)
1 more not listed.
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
- PointConv: Deep Convolutional Networks on 3D Point Clouds (CVPR 2019 · similarity 0.89)
- A-CNN: Annularly Convolutional Neural Networks on Point Clouds (CVPR 2019 · similarity 0.88)
- PointConvFormer: Revenge of the Point-Based Convolution (CVPR 2023 · similarity 0.88)
- PointCNN: Convolution On X-Transformed Points (NeurIPS 2018 · similarity 0.88)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017 · similarity 0.88)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.85)
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.
