| name | 3d | 3d | 16-bit | 16-bit | depth | depth | video | video | sub | sub | DS | AP | BEV | OS Yaw | Runtime [s] | code | code | title | authors | venue | description |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3D-GCK | yes | yes | no | no | no | no | no | no | no | no | 37.4 | 42.5 | 96.1 | 81.9 | 0.04 | no | no | Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time | Nils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim Denzler | IV 2020 | 3D-GCK is based on the standard SSD 2D object detection framework and lifts the 2D detections to 3D space by predicting additional regression and classification parameters. Hence, the runtime is kept close to pure 2D object detection. The additional parameters are transformed to 3D bounding box keypoints within the network under geometric constraints. 3D-GCK features a full 3D description including all three angles of rotation without supervision by any labeled ground truth data for the object's orientation, as it focuses on certain keypoints within the image plane. more details |
| HW-Noah-AVPNet2.3 | yes | yes | no | no | no | no | no | no | no | no | 40.1 | 43.5 | 96.0 | 88.0 | 0.04 | no | no | Anonymous | more details |
||
| iFlytek-ZBGKRD-fcos3d-depth-norm | yes | yes | no | no | no | no | no | no | no | no | 42.9 | 47.6 | 96.6 | 80.4 | n/a | no | no | Anonymous | more details |
| name | 3d | 3d | 16-bit | 16-bit | depth | depth | video | video | sub | sub | code | code | title | authors | venue | description | Runtime [s] | DS | AP | BEV | OS Yaw | OS PitchRoll | SizeSim |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3D-GCK | yes | yes | no | no | no | no | no | no | no | no | no | no | Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time | Nils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim Denzler | IV 2020 | 3D-GCK is based on the standard SSD 2D object detection framework and lifts the 2D detections to 3D space by predicting additional regression and classification parameters. Hence, the runtime is kept close to pure 2D object detection. The additional parameters are transformed to 3D bounding box keypoints within the network under geometric constraints. 3D-GCK features a full 3D description including all three angles of rotation without supervision by any labeled ground truth data for the object's orientation, as it focuses on certain keypoints within the image plane. more details | 0.04 | 37.4 | 42.5 | 96.1 | 81.9 | 100.0 | 70.7 |
| HW-Noah-AVPNet2.3 | yes | yes | no | no | no | no | no | no | no | no | no | no | Anonymous | more details | 0.04 | 40.1 | 43.5 | 96.0 | 88.0 | 100.0 | 82.1 | ||
| iFlytek-ZBGKRD-fcos3d-depth-norm | yes | yes | no | no | no | no | no | no | no | no | no | no | Anonymous | more details | n/a | 42.9 | 47.6 | 96.6 | 80.4 | 100.0 | 80.4 |
| name | 3d | 3d | 16-bit | 16-bit | depth | depth | video | video | sub | sub | code | code | title | authors | venue | description | Runtime [s] | all | car | truck | bus | train | motorcycle | bicycle |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3D-GCK | yes | yes | no | no | no | no | no | no | no | no | no | no | Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time | Nils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim Denzler | IV 2020 | 3D-GCK is based on the standard SSD 2D object detection framework and lifts the 2D detections to 3D space by predicting additional regression and classification parameters. Hence, the runtime is kept close to pure 2D object detection. The additional parameters are transformed to 3D bounding box keypoints within the network under geometric constraints. 3D-GCK features a full 3D description including all three angles of rotation without supervision by any labeled ground truth data for the object's orientation, as it focuses on certain keypoints within the image plane. more details | 0.04 | 37.4 | 67.5 | 29.0 | 32.3 | 23.1 | 32.9 | 39.9 |
| HW-Noah-AVPNet2.3 | yes | yes | no | no | no | no | no | no | no | no | no | no | Anonymous | more details | 0.04 | 40.1 | 77.2 | 30.0 | 29.9 | 24.5 | 37.2 | 42.0 | ||
| iFlytek-ZBGKRD-fcos3d-depth-norm | yes | yes | no | no | no | no | no | no | no | no | no | no | Anonymous | more details | n/a | 42.9 | 75.8 | 33.3 | 41.7 | 23.6 | 39.6 | 43.5 |