Multi-stage point completion network with critical set supervision

• Published in: Computer aided geometric design 2020-10, Vol.82, p.101925, Article 101925
• Main Authors: Zhang, Wenxiao, Long, Chengjiang, Yan, Qingan, Chow, Alix L.H., Xiao, Chunxia
• Format: Article
• Language: English
• Subjects: Deep learning; Point cloud; Shape completion
• ISSN: 0167-8396; 1879-2332
• DOI: 10.1016/j.cagd.2020.101925

•A general multi-stage network (MSPCN) is proposed which generates a cascade of multi-resolution point clouds.•A combining strategy to determine critical sets is devised to explore the critical points in an unsupervised manner.•Experiments demonstrate that combined with critical points supervision strategy, our network outperforms state-of-the-art methods. Point cloud based shape completion has great significant application values and refers to reconstructing a complete point cloud from a partial input. In this paper, we propose a multi-stage point completion network (MSPCN) with critical set supervision. In our network, a cascade of upsampling units is used to progressively recover the high-resolution results with several stages. Different from the existing works that generate the output point cloud structure supervised by the complete ground truth, we leverage the critical set at each stage for supervision and generate a more informative and useful intermediate outputs for the next stage. We propose a strategy by combining max-pooling selected points and volume-downsampling points to determine critical sets (MVCS) for supervision, which concerns both critical features and the shape of the model. We conduct extensive experiments on the ShapeNet dataset and the experimental results clearly demonstrate that our proposed MSPCN with critical set supervision outperforms the state-of-the-art completion methods.