Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud [article]

Weijing Shi, Ragunathan Rajkumar
2020 arXiv   pre-print
In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud. Towards this end, we encode the point cloud efficiently in a fixed radius near-neighbors graph. We design a graph neural network, named Point-GNN, to predict the category and shape of the object that each vertex in the graph belongs to. In Point-GNN, we propose an auto-registration mechanism to reduce translation variance, and also design a box merging and scoring operation to combine detections from
more » ... tiple vertices accurately. Our experiments on the KITTI benchmark show the proposed approach achieves leading accuracy using the point cloud alone and can even surpass fusion-based algorithms. Our results demonstrate the potential of using the graph neural network as a new approach for 3D object detection. The code is available https://github.com/WeijingShi/Point-GNN.
arXiv:2003.01251v1 fatcat:jo2mgerobnbjlmecnqhoiujjvi