Abstract: Compared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full track ...

Abstract: 3D object detection is considered as computationally expensive problem as it heavily relies on processing extensive sensory data making it unsuitable for the real-time application. To ...

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features ...