3D Object Detection Models


Introduced by Yin et al. in Center-based 3D Object Detection and Tracking

CenterPoint is a two-stage 3D detector that finds centers of objects and their properties using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation and velocity. In a second-stage, it refines these estimates using additional point features on the object. CenterPoint uses a standard Lidar-based backbone network, i.e., VoxelNet or PointPillars, to build a representation of the input point-cloud. CenterPoint predicts the relative offset (velocity) of objects between consecutive frames, which are then linked up greedily -- so in Centerpoint, 3D object tracking simplifies to greedy closest-point matching.

Source: Center-based 3D Object Detection and Tracking


Paper Code Results Date Stars


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign