KITTI-360
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Semantic Segmentation | KITTI-360 (val) | mIoU66.1 | 36 | |
| Semantic Segmentation | KITTI-360 (test) | mIoU69.71 | 25 | |
| Point Cloud Completion | KITTI-360 | IoU44.11 | 15 | |
| 3D Object Detection | KITTI-360 (val) | AP3D @ IoU=0.5, Class=Large26.77 | 11 | |
| Novel View Synthesis | KITTI-360 (val) | PSNR23.26 | 10 | |
| Object Reconstruction | KITTI-360 4-50m (long range evaluation) | Object Accuracy86 | 10 | |
| Object Reconstruction | KITTI-360 4-20m (short range evaluation) | Oacc92 | 10 | |
| Driving Scene Reconstruction | KITTI-360 | PSNR25.62 | 10 | |
| 3D Object Detection | KITTI-360 (test) | AP3D @ 50 IoU4.64 | 10 | |
| Novel View Synthesis | KITTI-360 static (val) | PSNR23.36 | 9 | |
| Lidar-Camera Extrinsic Calibration | KITTI-360 SFL + SFR | Angular Error (deg)0.709 | 8 | |
| Unconditional LiDAR Generation | KITTI-360 19 | FRD138.62 | 8 | |
| Pose estimation | KITTI-360 | RPE Translation (cm)5.449 | 8 | |
| Novel LiDAR View Synthesis | KITTI-360 | Point Cloud CD0.1089 | 8 | |
| Mono-view synthesis | KITTI-360 | PSNR25.62 | 8 | |
| Semantic Segmentation | KITTI-360 RGB-L (test) | mIoU66.1 | 8 | |
| Monocular 3D Object Detection | KITTI-360 (test) | AP BEV @ IoU 0.3 (Easy)69.7 | 7 | |
| BEV Segmentation | KITTI-360 (val) | BEV Seg IoU Large100 | 7 | |
| Amodal Panoptic Segmentation | KITTI-360 APS (val) | APQ42.9 | 7 | |
| Point Cloud Denoising | KITTI-360 (test) | DCD0.327 | 7 | |
| Unconditional LiDAR Generation | KITTI-360 (train-val) | FSVD71.69 | 6 | |
| Video Semantic Segmentation | KITTI-360 (test) | mIoU47.71 | 6 | |
| Surface Reconstruction | KITTI-360 static scenes 2021 | Seq 31 P->M Error (m)0.08 | 6 | |
| Segment Classification | KITTI-360 (base queries) | Accuracy75.7 | 6 | |
| Novel View Semantic Synthesis | KITTI-360 novel view synthesis | Semantic mIoU0.7507 | 6 |
Showing 25 of 56 rows