Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]
I removed Coordconv when training centermap task independently, the training loss similar to the network with Coordconv, but the centermap seems to get bad on the test set.
I removed Coordconv when training centermap task independently, the training loss similar to the network with Coordconv, but the centermap seems to get bad on the test set.