HyperPocket: Generative Point Cloud Completion


Scanning real-life scenes with modern registration devices typically give incomplete point cloud representations, mostly due to the limitations of the scanning process and 3D occlusions. Therefore, completing such partial representations remains a fundamental challenge of many computer vision applications. Most of the existing approaches aim to solve this problem by learning to reconstruct individual 3D objects in a synthetic setup of an uncluttered environment, which is far from a real-life scenario. In this work, we reformulate the problem of point cloud completion into an objects hallucination task. Thus, we introduce a novel autoencoder-based architecture called HyperPocket that disentangles latent representations and, as a result, enables the generation of multiple variants of the completed 3D point clouds. Furthermore, we split point cloud processing into two disjoint data streams and leverage a hypernetwork paradigm to fill the spaces, dubbed pockets, that are left by the missing object parts. As a result, the generated point clouds are smooth, plausible, and geometrically consistent with the scene. Moreover, our method offers competitive performances to the other state-of-the-art models, enabling a plethora of novel applications.


					@INPROCEEDINGS{9981829,  author={Spurek, P. and Kasymov, A. and Mazur, M. and Janik, D. and Tadeja, S.K. and Struski, Ł. and Tabor, J. and Trzciński, T.},  booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},   title={HyperPocket: Generative Point Cloud Completion},   year={2022},  volume={},  number={},  pages={6848-6853},  doi={10.1109/IROS47612.2022.9981829}}
APA Reference
Spurek, P., Kasymov, A., Mazur, M., Janik, D., Tadeja, S., Struski, Ł., Tabor, J., & Trzciński, T. (2022). HyperPocket: Generative Point Cloud Completion. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 6848-6853).

Cyber-human Lab Contributors

Dr Sławomir Tadeja

Slawomir K. Tadeja is a postdoctoral research associate in the Cyber-Human Lab belonging to the Institute of Manufacturing at the University of Cambridge. Previously...