Journal
PROCEEDINGS OF THE 2019 31ST CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2019)
Volume -, Issue -, Pages 4604-4609Publisher
IEEE
DOI: 10.1109/ccdc.2019.8832956
Keywords
Shape Completion; Point Completion Network; Point Cloud; PointNet
Funding
- National Natural Science Foundation [01673265]
- Special research projects for civil aircraft [MJ-2017-S-38]
- Aeronautical Science Foundation of China [20170157001]
- CE-MEE [2019G0302]
- 2018 State Key Laboratory of ocean engineering-SJTU
Ask authors/readers for more resources
3D shape completion by deep neural networks has been arousing increasing interest among research community. In this paper, A novel neural network architecture with multistage loss function that directly works on point clouds is proposed to map partial input point clouds to complete point clouds. Specifically, our network architecture not only works like an autoencoder that preserves the partial input. but also learns the global feature and fills the missing region. Experiments demonstrate the effectiveness of our approach on producing dense complete output point clouds with realistic structures in missing areas.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available