KITTI360
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-based position localization | KITTI360 Pose (test) | Localization Recall (k=1, ε < 5m)52 | 21 | |
| Text-to-point cloud localization | KITTI360 Pose (val) | Recall@k=1 (5m)54 | 19 | |
| Point Map Estimation | KITTI360 | Accuracy1.097 | 12 | |
| Depth Map Estimation | KITTI360 | Relative Error (Rel)9.1 | 12 | |
| Localization | KITTI360Pose (val) | Recall @ 5m83 | 12 | |
| Unconditional LiDAR Generation | KITTI360 (val) | FSVD35.8 | 11 | |
| Fine Localization | KITTI360Pose (test) | Recall@1 (5m)0.51 | 10 | |
| Fine Localization | KITTI360Pose (val) | Recall@k=1 (5m Error)54 | 10 | |
| Text-to-point cloud submap retrieval | KITTI360Pose (val) | Recall@154 | 9 | |
| Beyond-FoV Scene Estimation (Outer FoV Expansion) | KITTI360 seq10 (test) | PSNR20.5 | 9 | |
| Beyond-FoV Scene Estimation (Inner FoV Expansion) | KITTI360 seq10 (test) | PSNR37.38 | 8 | |
| Visual Odometry | KITTI360 (Seq. 00) | Rotational Error (Rerr)3.9 | 8 | |
| Global Place Recognition | KITTI360 Pose (test) | Recall@132 | 5 | |
| Semantic Segmentation | KITTI360 Unseen region (test) | mIoU39.62 | 4 | |
| Front-Image-Conditioned LiDAR Generation | KITTI360 | FSVD32.5 | 3 |
Showing 15 of 15 rows