Research map / Point clouds / Point cloud classification
SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel
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 |
|---|---|---|---|
| Add fuzzy elevation and self-convolution coefficients to the spherical kernel (ablation) | SegGCN on S3DIS Area 5 · S3DIS Area 5 | mIoU: 62.9 -> 63.6 | Helped |
| Add fuzzy elevation and self-convolution coefficients to the spherical kernel (ablation) | SegGCN on S3DIS Area 5 · S3DIS Area 5 | mAcc: 69.6 -> 70.4 | Helped |
| Use fuzzy assignments rather than hard assignments in KPConv (ablation) | SegGCN with KPConv kernel · S3DIS Area 5 | mIoU: 60.5 -> 61.0 | Helped |
| Replace the single 1×1 decoder convolution with 2× ResNet blocks (ablation) | SegGCN · S3DIS Area 5 | mIoU: 63.6 -> 62.9 | Hurt |
| Replace the single 1×1 decoder convolution with 2× ResNet blocks (ablation) | SegGCN · S3DIS Area 5 | mAcc: 70.4 -> 69.8 | Hurt |
| Use fuzzy rather than hard spherical kernels when input points are dropped (ablation) | SegGCN · S3DIS Area 5 with point dropping | mIoU standard deviation across input sizes: 1.66 -> 0.37 | Helped |
| Use SegGCN rather than KPConv | 3D segmentation · S3DIS Area 5 | mIoU: 65.4 -> 63.6 | Hurt |
| Use SegGCN rather than SparseConvNet | 3D segmentation · ScanNet | mIoU: 72.5 -> 58.9 | Hurt |
Closest papers by meaning
- Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis (CVPR 2020 · similarity 0.88)
- X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition (CVPR 2024 · similarity 0.86)
- Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation (AAAI 2025 · similarity 0.85)
- Rethinking Few-shot 3D Point Cloud Semantic Segmentation (CVPR 2024 · similarity 0.85)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.85)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · 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.