Temp 3d Box


name3d3d16-bit16-bitdepthdepthvideovideosubsubDSAPBEVOS YawRuntime [s]codecodetitleauthorsvenuedescription
3D-GCKyesyesnononononononono37.442.596.181.90.04nonoSingle-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-TimeNils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim DenzlerIV 20203D-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-AVPNet2.3yesyesnononononononono40.143.596.088.00.04nonoAnonymous
more details
iFlytek-ZBGKRD-fcos3d-depth-normyesyesnononononononono42.947.696.680.4n/anonoAnonymous
more details
name3d3d16-bit16-bitdepthdepthvideovideosubsubcodecodetitleauthorsvenuedescriptionRuntime [s]DSAPBEVOS YawOS PitchRollSizeSim
3D-GCKyesyesnonononononononononoSingle-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-TimeNils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim DenzlerIV 20203D-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
0.0437.442.596.181.9100.070.7
HW-Noah-AVPNet2.3yesyesnonononononononononoAnonymous
more details
0.0440.143.596.088.0100.082.1
iFlytek-ZBGKRD-fcos3d-depth-normyesyesnonononononononononoAnonymous
more details
n/a42.947.696.680.4100.080.4
name3d3d16-bit16-bitdepthdepthvideovideosubsubcodecodetitleauthorsvenuedescriptionRuntime [s]allcartruckbustrainmotorcyclebicycle
3D-GCKyesyesnonononononononononoSingle-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-TimeNils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim DenzlerIV 20203D-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
0.0437.467.529.032.323.132.939.9
HW-Noah-AVPNet2.3yesyesnonononononononononoAnonymous
more details
0.0440.177.230.029.924.537.242.0
iFlytek-ZBGKRD-fcos3d-depth-normyesyesnonononononononononoAnonymous
more details
n/a42.975.833.341.723.639.643.5