Point Cloud Registration With Object-Centric Alignment

Abstract

Point cloud registration is a core task in 3D perception, which aims to align two point clouds. Moreover, the registration of point clouds with low overlap represents a harder challenge, where previous methods tend to fail. Recent deep learning-based approaches attempt to overcome this issue by learning to find overlapping regions in the whole scene. However, they still lack robustness and accuracy, and thus might not be suitable for real-world applications. Therefore, we present a novel registration pipeline that focuses on object-level alignment to provide a robust and accurate alignment of point clouds. By extracting and completing the missing points of the object of interest, a rough alignment can be achieved even for point clouds with low overlap captured from widely apart viewpoints. We provide a quantitative and qualitative evaluation on synthetic and real-world data captured with a Kinect v2. The proposed approach outperforms the current the current state-of-the-art methods by more than 29% w.r.t. the registration recall on the introduced synthetic dataset. We show that the overall performance and robustness increases due to the object-level alignment, while the baselines perform poorly as they take the entire scene into account.

Keywords

• Point cloud registration
• sensor fusion
• 3D reconstruction
• deep learning