Research map / Point clouds / Segmentation and detection
Learning Temporal Variations for 4D Point Cloud Segmentation
Hanyu Shi, Jiacheng Wei, Hao Wang, Fayao Liu, Guosheng Lin
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 temporal variation-aware interpolation (TVI) (ablation) | Backbone-14 · SemanticKITTI val | mIoU: 50.0 -> 50.7 | Improved |
| add TVI (ablation) | Backbone-34 · SemanticKITTI val | mIoU: 51.5 -> 52.3 | Improved |
| add temporal voxel-point refiner (TVPR) (ablation) | Backbone-14+TVI · SemanticKITTI val | mIoU: 50.7 -> 52.4 | Improved |
| add TVPR (ablation) | Backbone-34+TVI · SemanticKITTI val | mIoU: 52.3 -> 53.8 | Improved |
| add TVI (ablation) | Backbone-34 · SemanticPOSS | mIoU: 60.2 -> 61.9 | Improved |
| add TVPR (ablation) | Backbone-34+TVI · SemanticPOSS | mIoU: 61.9 -> 63.0 | Improved |
| add temporal frames to MinkUNet-34 (SpSequenceNet-style backbone) (ablation) | MinkUNet-34 · SemanticKITTI val | mIoU: 51.0 -> 51.5 | Improved |
| add temporal frames to MinkUNet-14 (ablation) | MinkUNet-14 · SemanticKITTI val | mIoU: 47.5 -> 50.0 | Improved |
| add TVI (ablation) | Backbone-34 · SemanticKITTI val person IoU | IoU: 24.1 -> 18.1 | Hurt |
| add TVI (ablation) | Backbone-34 · SemanticKITTI val moving-car IoU | IoU: 71.4 -> 73.6 | Improved |
| add TVPR (ablation) | Backbone-34+TVI · SemanticKITTI val bicycle IoU | IoU: 28.0 -> 40.4 | Improved |
| use 7 instead of 5 neighbours in TVI (ablation) | TVI · SemanticKITTI val | mIoU | 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.
- SpSequenceNet — SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds (CVPR 2020) · better on 2 of 2 shared results
- RandLA-Net — RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020) · 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
- 4D Panoptic LiDAR Segmentation (CVPR 2021 · similarity 0.91)
- Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving (CVPR 2023 · similarity 0.91)
- Exploiting the Benefits of Temporal Information in the Realm of LiDAR Panoptic Segmentation (TPAMI 2025 · similarity 0.90)
- Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation (CVPR 2023 · similarity 0.90)
- Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving (CVPR 2023 · similarity 0.90)
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception (NeurIPS 2025 · similarity 0.90)
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.
