Research map / Point clouds / Segmentation and detection
Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks
Maosheng Ye, Rui Wan, Shuangjie Xu, Tongyi Cao, Qifeng Chen
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 |
|---|---|---|---|
| add multi-scale sparse projection (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 64.0 -> 65.8 | Improved |
| add attentive scale selection (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 65.8 -> 67.7 | Improved |
| add deep sparse supervision (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 67.7 -> 69.4 | Improved |
| use attentive scale selection instead of tensor sum (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 67.7 -> 69.4 | Improved |
| use attentive scale selection instead of concatenation (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 68.7 -> 69.4 | Improved |
| use sparse instead of dense supervision (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 69.5 -> 69.4 | No clear effect |
| add deep sparse supervision | SPVCNN · SemanticKITTI val (ablation) | mIoU: 64.7 -> 66.1 | Improved |
| add deep sparse supervision | DRINet · SemanticKITTI val (ablation) | mIoU: 67.3 -> 68.1 | Improved |
| add deep sparse supervision | Cylinder3D · SemanticKITTI val (ablation) | mIoU: 66.5 -> 67.8 | Improved |
| add attentive scale selection | SPVCNN · SemanticKITTI val (ablation) | mIoU: 64.7 -> 66.7 | Improved |
| add attentive scale selection | DRINet · SemanticKITTI val (ablation) | mIoU: 67.3 -> 67.9 | Improved |
| increase blocks from 4 to 5 (ablation) | GASN · SemanticKITTI val (ablation) | mIoU: 69.4 -> 69.9 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DRINet — DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation (ICCV 2021) · better on 3 of 3 shared results
- RPVNet — RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation (ICCV 2021) · better on 3 of 3 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
- Deep FusionNet for Point Cloud Semantic Segmentation (ECCV 2020 · similarity 0.89)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017 · similarity 0.89)
- SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds (ECCV 2022 · similarity 0.88)
- 3D Semantic Segmentation With Submanifold Sparse Convolutional Networks (CVPR 2018 · similarity 0.88)
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR 2018 · similarity 0.88)
- Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations (AAAI 2025 · similarity 0.87)
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.
