Graph-Guided Deformation for Point Cloud Completion

For a long time, the point cloud completion task has been regarded as pure generation task. After obtaining global shape code through encoder, complete is generated using priorly learnt by networks. However, such models are undesirably biased towards prior average objects and inherently limited to fit geometry details. In this letter, we propose Graph-Guided Deformation Network, which respectively regards input data intermediate controlling supporting points, optimization guided graph convolutional network(GCN) for Our key insight simulate least square Laplacian deformation process via mesh methods, brings adaptivity modeling variation in By means, also reduce gap between algorithms. As far know, first refine mimicing traditional graphics algorithms with GCN-guided deformation. We have conducted extensive experiments on both simulated indoor dataset ShapeNet, outdoor KITTI, our self-collected autonomous driving Pandar40. The results show that method outperforms existing state-of-the-art 3D