Unpaired Point Cloud Completion on Real Scans using Adversarial Training

Xuelin Chen, Baoquan Chen, Niloy J. Mitra

Keywords: adversarial, gan

Abstract: As 3D scanning solutions become increasingly popular, several deep learning setups have been developed for the task of scan completion, i.e., plausibly filling in regions that were missed in the raw scans. These methods, however, largely rely on supervision in the form of paired training data, i.e., partial scans with corresponding desired completed scans. While these methods have been successfully demonstrated on synthetic data, the approaches cannot be directly used on real scans in absence of suitable paired training data. We develop a first approach that works directly on input point clouds, does not require paired training data, and hence can directly be applied to real scans for scan completion. We evaluate the approach qualitatively on several real-world datasets (ScanNet, Matterport3D, KITTI), quantitatively on 3D-EPN shape completion benchmark dataset, and demonstrate realistic completions under varying levels of incompleteness.

Similar Papers

Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
Lukas Prantl, Nuttapong Chentanez, Stefan Jeschke, Nils Thuerey,
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model
Wenhan Xiong, Jingfei Du, William Yang Wang, Veselin Stoyanov,