3D point cloud completion is very challenging because it heavily relies on the accurate understanding of the complex 3D shapes (e.g., high-curvature, concave/convex, and hollowed-out 3D shapes) and the unknown & diverse patterns of the partially available point clouds. In this paper, we propose a novel solution,i.e., Point-block Carving (PC), for completing the complex 3D point cloud completion. Given the partial point cloud as the guidance, we carve a3D block that contains the uniformly distributed 3D points, yielding the entire point cloud. To achieve PC, we propose a new network architecture, i.e., CarveNet. This network conducts the exclusive convolution on each point of the block, where the convolutional kernels are trained on the 3D shape data. CarveNet determines which point should be carved, for effectively recovering the details of the complete shapes. Furthermore, we propose a sensor-aware method for data augmentation,i.e., SensorAug, for training CarveNet on richer patterns of partial point clouds, thus enhancing the completion power of the network. The extensive evaluations on the ShapeNet and KITTI datasets demonstrate the generality of our approach on the partial point clouds with diverse patterns. On these datasets, CarveNet successfully outperforms the state-of-the-art methods.

翻译：3D点云的完成非常具有挑战性, 因为它在很大程度上依赖于对复杂的 3D 形状( 如高精度、 comcave/ convex 和空外 3D 形状) 和部分可用点云的未知和不同模式的准确理解。 在本文中, 我们提出了一个新的解决方案, 即 点块刻录( PC ), 用于完成复杂的 3D 点云的完成。 鉴于部分点云作为指导, 我们刻出包含统一分布的 3D 点的 A3D 块块, 产生整个点云。 为了实现 PC, 我们提议一个新的网络结构, 即 CarveNet 。 这个网络在块的每个点上进行独家化的变换, 在 3D 形状数据数据中训练 。 CarveNet 确定应该刻出哪个点, 以有效恢复完整形状的细节 。 此外, 我们提出一个包含统一分布的 3D 3D 点, 并生成整个点的 CARveelNet 。 我们提议一个包含 CaveNet 在部分点 模式上培训 CarveNet 的Carve, 、 adline 和 KSqreveletaltaltaltal develys a strut the sup the pass compal compeal compeals.