Research map / Point clouds / Segmentation and detection
SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds
Yanbo Wang, Wentao Zhao, Cao Chuan, Tianchen Deng, Jingchuan Wang, Weidong 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 sparse focal point modulation to SSCN basic blocks (ablation) | SFPNet · nuScenes val | mIoU: 75.4 -> 80.1 | Improved |
| add third focal level (ablation) | SFPNet · nuScenes val | mIoU: 78.2 -> 80.1 | Improved |
| add global average pooling context (ablation) | SFPNet · nuScenes val | mIoU: 78.1 -> 80.1 | Improved |
| add SFPM on S.MID hybrid-solid LiDAR data (ablation) | SFPNet · S.MID val | mIoU: 67.6 -> 71.9 | Improved |
| use specially designed inductive bias (radial window, cylindrical partition) on hybrid-solid LiDAR | SphereFormer, Cylinder3D · S.MID val | mIoU: SSCN 67.6 -> 67.8 and 68.8 | No clear effect |
| replace window-attention with focal modulation, solid-state LiDAR | SFPNet vs SphereFormer · PandaSet val | mIoU: 63.5 -> 64.0 | Improved |
| SFPNet versus SphereFormer on mechanical spinning LiDAR test sets | SFPNet · nuScenes test / SemanticKITTI test | mIoU: nuScenes 81.9 -> 80.2; SemanticKITTI 74.8 -> 70.3 | Hurt |
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.
- 2DPASS — 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) · better on 1 of 1 shared result
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
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020 · similarity 0.91)
- Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation (ICCV 2023 · similarity 0.91)
- SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation (ICCV 2023 · similarity 0.90)
- Open-World Semantic Segmentation for LIDAR Point Clouds (ECCV 2022 · similarity 0.90)
- LaserMix for Semi-Supervised LiDAR Semantic Segmentation (CVPR 2023 · similarity 0.90)
- PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (AAAI 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.
