Research map / Point clouds / Segmentation and detection
TempNet: Online Semantic Segmentation on Large-Scale Point Cloud Series
Yunsong Zhou, Hongzi Zhu, Chunqin Li, Tiankai Cui, Shan Chang, Minyi Guo
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 TempNet (*2) | PointNet++ · SemanticKITTI test (sequences 09-10) | mIoU (%): 20.5 -> 26.9 | Improved |
| add TempNet (*2) | GACNet · SemanticKITTI test (sequences 09-10) | mIoU (%): 28.8 -> 32.8 | Improved |
| add TempNet (*2) | SqueezeSegV2 · SemanticKITTI test (sequences 09-10) | mIoU (%): 39.7 -> 44.4 | Improved |
| add TempNet (*2) | DarkNet53Seg · SemanticKITTI test (sequences 09-10) | mIoU (%): 49.3 -> 52.5 | Improved |
| add TempNet (*2) | RandLA-Net · SemanticKITTI test (sequences 09-10) | mIoU (%): 52.4 -> 55.8 | Improved |
| add TempNet (*2) | PointNet++ · SemanticKITTI test (sequences 09-10) | running time (ms): 328 -> 375 | Hurt |
| add partial feature update on non-key frames (DFP to *2) (ablation) | TempNet on SqueezeSegV2 · SemanticKITTI (SqueezeSegV2, aggregation schemes) | IoU avg: 38.77 -> 44.43 | Improved |
| add partial feature update on non-key frames (DFP to *2) (ablation) | TempNet on SqueezeSegV2 · SemanticKITTI (SqueezeSegV2, aggregation schemes) | online time (ms): 309 -> 1475 | Hurt |
| add adaptive frame scheduling with key frames (*1 to *2) (ablation) | TempNet on SqueezeSegV2 · SemanticKITTI (SqueezeSegV2, aggregation schemes) | IoU avg: 41.89 -> 44.43 | Improved |
| add adaptive frame scheduling with key frames (*1 to *2) (ablation) | TempNet on SqueezeSegV2 · SemanticKITTI (SqueezeSegV2, aggregation schemes) | online time (ms): 270 -> 1475 | Hurt |
| use sparse key frames instead of dense feature aggregation (DFA to *2) (ablation) | TempNet on SqueezeSegV2 · SemanticKITTI (SqueezeSegV2, aggregation schemes) | online time (ms): 2996 -> 1475 | Improved |
| use sparse key frames instead of dense feature aggregation (DFA to *2) (ablation) | TempNet on SqueezeSegV2 · SemanticKITTI (SqueezeSegV2, aggregation schemes) | Acc avg (%): 88.1 -> 87.5 | 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.
- RandLA-Net — RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020) · 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
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020 · similarity 0.88)
- Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving (AAAI 2022 · similarity 0.88)
- Low-Latency Video Semantic Segmentation (CVPR 2018 · similarity 0.88)
- Efficient Outdoor 3D Point Cloud Semantic Segmentation for Critical Road Objects and Distributed Contexts (ECCV 2020 · similarity 0.87)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.86)
- Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation (AAAI 2025 · similarity 0.86)
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.
