4D Panoptic LiDAR Segmentation on SemanticKITTI (test)
70.3LSTQICP-4D
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| ICP-4D2025.12 | 70.3 | — | — | — | — | 70 | 70.5 | |
| Mask4Former* + ICP-4DNumber of Scans=1, Association Training=false2025.12 | 70.3 | 70 | 70.5 | 72.7 | 67.4 | — | — | |
| YAKD2025.12 | 68.6 | — | — | — | — | 70.8 | 66.5 | |
| hphnngcquan2025.12 | 68.5 | — | — | — | — | 70.4 | 66.7 | |
| KadirYilmaz2025.12 | 68.4 | — | — | — | — | 67.3 | 69.6 | |
| Mask4FormerNumber of Scans=2, Association Training=false2025.12 | 68.4 | 67.3 | 69.6 | 72.7 | 65.3 | — | — | |
| ConOcc2025.12 | 67.9 | — | — | — | — | 68.3 | 67.4 | |
| Eq-4D-StOPNumber of Scans=4, Association Training=false2025.12 | 67 | 72 | 62.4 | 69.1 | 60.9 | — | — | |
| Mask4Former* + CA-Net*Number of Scans=1, Association Training=true2025.12 | 66.5 | 62.8 | 70.5 | 72.7 | 67.4 | — | — | |
| Mask4DNumber of Scans=1, Association Training=true2025.12 | 64.3 | 66.4 | 62.2 | 69.9 | 52.2 | — | — | |
| 4D-StOPNumber of Scans=4, Association Training=false2025.12 | 63.9 | 69.5 | 58.8 | 67.7 | 53.8 | — | — | |
| DS-Net + ICP-4DNumber of Scans=1, Association Training=false2025.12 | 62.9 | 65.3 | 60.6 | 66.9 | 52 | — | — | |
| 4D-DS-Net2022.03 | 62.3 | 65.8 | 58.9 | 65.6 | 49.8 | — | — | |
| DS-Net + CA-NetNumber of Scans=1, Association Training=true2025.12 | 62.1 | 63.7 | 60.6 | 66.9 | 52 | — | — | |
| 4D-PLS2022.03 | 56.9 | 56.4 | 57.4 | 66.9 | 51.6 | — | — | |
| 4D-PLSNumber of Scans=4, Association Training=false2025.12 | 56.9 | 56.4 | 57.4 | 66.9 | 51.6 | — | — | |
| KP + PP + SFPSemantic Segmentation=KPConv, Detection=PointPillars, Tracking=Scene Flow based Propagation2022.03 | 38.5 | 26.6 | 55.9 | 66.9 | 47.7 | — | — | |
| KPConv+PP+SFPNumber of Scans=1, Association Training=true2025.12 | 38.5 | 26.6 | 55.9 | 66.9 | 47.7 | — | — | |
| KP + PP + MOTSemantic Segmentation=KPConv, Detection=PointPillars, Tracking=Multi-Object Tracking2022.03 | 38 | 25.9 | 55.9 | 66.9 | 47.7 | — | — | |
| KPConv+PP+MOTNumber of Scans=1, Association Training=true2025.12 | 38 | 25.9 | 55.9 | 66.9 | 47.7 | — | — | |
| RN + PP + MOTSemantic Segmentation=RangeNet++, Detection=PointPillars, Tracking=Multi-Object Tracking2022.03 | 35.5 | 24.1 | 52.4 | 64.5 | 35.8 | — | — | |
| RN + PP + SFPSemantic Segmentation=RangeNet++, Detection=PointPillars, Tracking=Scene Flow based Propagation2022.03 | 34.9 | 23.3 | 52.4 | 64.5 | 35.8 | — | — | |
| DS-NetNumber of Scans=12025.12 | — | — | 60.6 | 66.9 | 52 | — | — | |
| Mask4Former*Number of Scans=12025.12 | — | — | 70.5 | 72.7 | 67.4 | — | — |