Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving

arXiv:2403.06166v1 Announce Type: new
Abstract: We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving. Traditional point-based 3D object detectors often employ architectures that rely on a progressive downsampling of points. While this method effectively reduces computational demands and increases receptive fields, it will compromise the preservation of crucial non-local information for accurate 3D object detection, especially in the complex driving scenarios. To address this, we introduce an intriguing Cross-Cluster Shifting operation …

3d object 3d object detection abstract architectures arxiv autonomous autonomous driving cluster computational cs.cv cs.ro detection downsampling driving object shift ssd type