Abstract: In recent years, point-based methods have achieved promising performance on 3D object detection task. Although effective, they still suffer from the inherent sparsity of point cloud, which ...

Abstract: Monocular 3D object detection has been studied as a promising task for diverse applications, such as autonomous driving, due to its lower cost and more straightforward configuration than ...

RadarMOTR is a transformer neural network based on MOTRv2 able to track multiple objects in Range-Doppler maps. Objects are first detected by an external detector based on CFAR & DBSCAN clustering.