Pre-Training by Completing Point Clouds
There has recently been a flurry of exciting advances in deep learning models on point clouds. However, these advances have been hampered by the difficulty of creating labelled point cloud datasets: sparse point clouds often have unclear label identities for certain points, while dense point clouds are time-consuming to annotate. Inspired by mask-based pre-training in the natural language processing community, we propose a novel pre-training mechanism for point clouds. It works by masking occluded points that result from observing the point cloud at different camera views. It then optimizes a completion model that learns how to reconstruct the occluded points, given the partial point cloud. In this way, our method learns a pre-trained representation that can identify the visual constraints inherently embedded in real-world point clouds. We call our method Occlusion Completion (OcCo). We demonstrate that OcCo learns representations that improve generalization on downstream tasks over prior pre-training methods, that transfer to different datasets, that reduce training time, and improve labelled sample efficiency. previous pre-training methods. Our code and dataset are available at https://github.com/hansen7/OcCo
READ FULL TEXT