O-Unet: An Octree-Based Convolutional Neural Network for 3-D Radar Point Clouds Reconstruction

Point cloud upsampling and surface reconstruction work has important implications in model generation and target recognition, indoor navigation and autonomous driving. In this paper, an auto-encoder(AE) network based on octree convolution network are proposed for target surface reconstruction with millimeter-wave (MMW) radar and LIDAR. In the scheme, we learn to generate point cloud data by a two-stage method. The input point cloud data is constructed as an octree, and the structure of the octree is estimated by the network. Then we construct the surface of the object by using the signed distance method by implicit function and learn the fine position information of the point cloud in the octree by the network, which realizes the upsampling of point clouds as well. Finally, we use the generated point cloud to achieve surface reconstruction.