Chen B.-FYeh Y.-MYI-CHANG LU2023-06-092023-06-09202215206149https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131229519&doi=10.1109%2fICASSP43922.2022.9746388&partnerID=40&md5=a2910df721876c6c113132323d8265b1https://scholars.lib.ntu.edu.tw/handle/123456789/632091Real-world point clouds usually have inconsistent orientations and often suffer from data missing issues. To solve this problem, we design a neural network, CF-Net, to address challenges in rotation invariant completion. In our network, we modify and integrate complementary operators to extract features that are robust against rotation and incompleteness. Our CF-Net can achieve competitive results both geometrically and semantically as demonstrated in this paper. © 2022 IEEEDeep learning; Point cloud completion; Rotation invariantconference paper10.1109/ICASSP43922.2022.97463882-s2.0-85131229519