Point Cloud Registration using Representative Overlapping Points
This addresses a key bottleneck in robotics and computer vision for tasks like object recognition and mapping, though it is an incremental improvement over existing learning-based methods.
The paper tackles the challenge of 3D point cloud registration with partial overlap by proposing ROPNet, a deep learning model that transforms partial-to-partial into partial-to-complete registration, achieving state-of-the-art performance on ModelNet40 with noisy and partially overlapping data.
3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such correspondences and meet great challenges with partial overlap. In this paper, we propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration that transforms partial-to-partial registration into partial-to-complete registration. Specifically, we propose a context-guided module which uses an encoder to extract global features for predicting point overlap score. To better find representative overlapping points, we use the extracted global features for coarse alignment. Then, we introduce a Transformer to enrich point features and remove non-representative points based on point overlap score and feature matching. A similarity matrix is built in a partial-to-complete mode, and finally, weighted SVD is adopted to estimate a transformation matrix. Extensive experiments over ModelNet40 using noisy and partially overlapping point clouds show that the proposed method outperforms traditional and learning-based methods, achieving state-of-the-art performance. The code is available at https://github.com/zhulf0804/ROPNet.