Feature Interactive Representation for Point Cloud Registration

Bingli Wu, Jie Ma, Gaojie Chen, Pei An; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 5530-5539

Abstract


Point cloud registration is the process of using the common structures in two point clouds to splice them together. To find out these common structures and make these structures match more accurately, we investigate the direction of interacting information of the source and target point clouds. To this end, we propose a Feature Interactive Representation learning Network (FIRE-Net), which can explore feature interaction among the source and target point clouds from different levels. Specifically, we first introduce a Combined Feature Encoder (CFE) based on feature interaction intra point cloud. CFE extracts interactive features intra each point cloud and combines them to enhance the ability of the network to describe the local geometric structure. Then, we propose a feature interaction mechanism inter point clouds which includes a Local Interaction Unit (LIU) and a Global Interaction Unit (GIU). The former is used to interact information between point pairs across two point clouds, thus the point features in one point cloud and its similar point features in another point cloud can be aware of each other. The latter is applied to change the per-point features depending on the global cross information of two point clouds, thus one point cloud has the global perception of another. Extensive experiments on partially overlapping point cloud registration show that our method achieves state-of-the-art performance.

Related Material


[pdf]
[bibtex]
@InProceedings{Wu_2021_ICCV, author = {Wu, Bingli and Ma, Jie and Chen, Gaojie and An, Pei}, title = {Feature Interactive Representation for Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {5530-5539} }