GRJointNET: Synergistic Completion and Part Segmentation on 3D Incomplete Point Clouds

Segmentation of three-dimensional (3D) point clouds is an important task for autonomous systems. However, success of segmentation algorithms depends greatly on the quality of the underlying point clouds (resolution, completeness etc.). In particular, incomplete point clouds might reduce a downstream model's performance. GRNet is proposed as a novel and recent deep solution to complete incomplete point clouds, but it is not capable of part segmentation. On the other hand, our proposed solution, GRJointNet, is an architecture that can perform joint completion and segmentation on point clouds as a successor of GRNet. Features extracted for the two tasks are also utilized by each other to increase the overall performance. We evaluated our proposed network on the ShapeNet-Part dataset and compared its performance to GRNet. Our results demonstrate GRJointNet outperforms GRNet on point completion. It should also be noted that GRNet is not capable of segmentation while GRJointNet is. This study therefore holds a promise to enhance practicality and utility of point clouds for 3D vision for autonomous systems.