SPCNet: Stepwise Point Cloud Completion Network
This addresses the challenge of repairing incomplete 3D objects for applications like computer vision and robotics, representing an incremental improvement with a novel training strategy.
The paper tackles the problem of point cloud completion for 3D models with large missing parts by proposing SPCNet, a stepwise network that iteratively recovers coarse to detailed shapes, achieving superior performance over state-of-the-art methods in experiments.
How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate the above physical repair procedure to address the point cloud completion task. We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings. SPCNet has a hierarchical bottom-to-up network architecture. It fulfills shape completion in an iterative manner, which 1) first infers the global feature of the coarse result; 2) then infers the local feature with the aid of global feature; and 3) finally infers the detailed result with the help of local feature and coarse result. Beyond the wisdom of simulating the physical repair, we newly design a cycle loss %based training strategy to enhance the generalization and robustness of SPCNet. Extensive experiments clearly show the superiority of our SPCNet over the state-of-the-art methods on 3D point clouds with large missings.