Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting

arXiv:2404.06700v1 Announce Type: new
Abstract: The emergence of Multi-Camera 3D Object Detection (MC3D-Det), facilitated by bird's-eye view (BEV) representation, signifies a notable progression in 3D object detection. Scaling MC3D-Det training effectively accommodates varied camera parameters and urban landscapes, paving the way for the MC3D-Det foundation model. However, the multi-view fusion stage of the MC3D-Det method relies on the ill-posed monocular perception during training rather than surround refinement ability, leading to what we term "surround refinement degradation". To this end, our …

3d object 3d object detection arxiv cs.cv detection object scaling through type