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.

Authors

• Przemyslaw Spurek
• Artur Kasymov
• Marcin Mazur
• Diana Janik
• Slawomir Konrad Tadeja
• Lukasz Struski
• Jacek Tabor
• Tomasz Trzcinski

Keywords

• Point cloud compression
• Computer vision
• Three-dimensional displays
• Computer architecture
• Task analysis
• Intelligent robots
• Point Cloud
• Point Cloud Completion
• Hallucinations
• Object Parts
• Latent Representation
• 3D Point Cloud
• Point Cloud Generation
• Uniform Distribution
• Objective Function
• Latent Space
• Representation Of Space
• Single Object
• Network Weights
• Target Object
• Unit Sphere
• Target Network
• Variational Autoencoder
• Real Scenes
• 3D Scene
• Disjoint Subsets
• Latent Code
• Versions Of Objects
• Occluded Objects
• Missing Parts
• Matching Distance
• Reconstruction Task
• Input Point Cloud