期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 33, 期 8, 页码 3585-3595出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2023.3237328
关键词
Point cloud; point cloud registration; correspondence filtering; point cloud feature interaction; partial overlap registration
In this paper, a skip-attention based correspondence filtering network (SACF-Net) is proposed for point cloud registration. It utilizes a feature interaction mechanism and attention mechanism to extract high-quality correspondences from different resolutions of the encoder, leading to unprecedented performance improvements on indoor and outdoor scene datasets.
Rigid registration is a transformation estimation problem between two point clouds. The two point clouds captured may partially overlap owing to different viewpoints and acquisition times. Some previous correspondence matching based methods utilize an encoder-decoder network to carry out partial-to-partial registration task and adopt a skip-connection structure to convey information between the encoder and decoder. However, equally revisiting them with skip-connection may introduce the information redundancy, and limit the feature learning ability of the entire network. To address these problems, we propose a skip-attention based correspondence filtering network (SACF-Net) for point cloud registration. A novel feature interaction mechanism is designed to utilize both low-level geometric information and high-level context-aware information to enhance the original pointwise matching map. Additionally, a skip-attention based correspondence filtering method is proposed to selectively revisits features in the encoder at different resolutions, allowing the decoder to extract high-quality correspondences within overlapping regions. We conduct comprehensive experiments on indoor and outdoor scene datasets, and the results show that the proposed SACF-Net yields unprecedented performance improvements.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据