PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration
This addresses a challenging computer vision problem for robotics and 3D reconstruction, but it is incremental as it builds on existing registration methods with a novel learning approach.
The paper tackles the problem of multi-instance point cloud registration, where multiple source instances must be aligned within a target point cloud, and proposes PointCLM, a contrastive learning-based framework that outperforms state-of-the-art methods by a large margin on synthetic and real datasets.
Multi-instance point cloud registration is the problem of estimating multiple poses of source point cloud instances within a target point cloud. Solving this problem is challenging since inlier correspondences of one instance constitute outliers of all the other instances. Existing methods often rely on time-consuming hypothesis sampling or features leveraging spatial consistency, resulting in limited performance. In this paper, we propose PointCLM, a contrastive learning-based framework for mutli-instance point cloud registration. We first utilize contrastive learning to learn well-distributed deep representations for the input putative correspondences. Then based on these representations, we propose a outlier pruning strategy and a clustering strategy to efficiently remove outliers and assign the remaining correspondences to correct instances. Our method outperforms the state-of-the-art methods on both synthetic and real datasets by a large margin.