DualGenerator: Information Interaction-based Generative Network for Point Cloud Completion
This work addresses the challenge of generating high-quality complete point clouds from incomplete data, which is important for applications like 3D reconstruction and robotics, but it is incremental as it builds on existing generative methods.
The paper tackles the problem of point cloud completion by proposing DualGenerator, a network that integrates adversarial and variational generation paths with local refinement to better capture structural and semantic information. It demonstrates superior performance on MVP and Completion3D datasets, with robustness against noise and sparse sampling.
Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features, ignoring spatial and semantic information of adjacent points. They cannot distinguish structural information well between different object parts, and the robustness of models is poor. To tackle these challenges, we propose an information interaction-based generative network for point cloud completion ($\mathbf{DualGenerator}$). It contains an adversarial generation path and a variational generation path, which interact with each other and share weights. DualGenerator introduces a local refinement module in generation paths, which captures general structures from partial inputs, and then refines shape details of the point cloud. It promotes completion in the unknown region and makes a distinction between different parts more obvious. Moreover, we design DGStyleGAN to improve the generation quality further. It promotes the robustness of this network combined with fusion analysis of dual-path completion results. Qualitative and quantitative evaluations demonstrate that our method is superior on MVP and Completion3D datasets. The performance will not degrade significantly after adding noise interference or sparse sampling.