Research map / Point clouds / Point cloud classification
Octree Guided CNN With Spherical Kernels for 3D Point Clouds
Huan Lei, Naveed Akhtar, Ajmal Mian
Check 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 spherical convolutional kernels with octree-guided feature extraction instead of the compared point-cloud methods | 3D object classification · ModelNet10 | class accuracy: 93.9 -> 94.4 | Improved |
| use spherical convolutional kernels with octree-guided feature extraction instead of the compared point-cloud methods | 3D object classification · ModelNet10 | instance accuracy: 94.4 -> 94.6 | Improved |
| use spherical convolutional kernels with octree-guided feature extraction instead of the compared point-cloud methods | 3D object classification · ModelNet40 | class accuracy: 87.3 -> 88.7 | Improved |
| use spherical convolutional kernels with octree-guided feature extraction instead of the compared point-cloud methods | 3D object classification · ModelNet40 | instance accuracy: 91.0 -> 92.0 | Improved |
| use spherical convolutional kernels with octree-guided feature extraction instead of the compared point-cloud methods | 3D part segmentation · ShapeNet part segmentation | mIoU: 85.1 -> 86.8 | Improved |
| use spherical convolutional kernels with octree-guided feature extraction instead of OctNet | semantic segmentation · RueMonge2014 | IoU: 59.2 -> 63.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SO-Net — SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018) · better on 2 of 2 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
- Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds (TPAMI 2020 · similarity 0.93)
- Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling (CVPR 2018 · similarity 0.88)
- A-CNN: Annularly Convolutional Neural Networks on Point Clouds (CVPR 2019 · similarity 0.88)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.86)
- TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis (CVPR 2024 · similarity 0.85)
- Sonata: Self-Supervised Learning of Reliable Point Representations (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.
