A Strong Baseline for Point Cloud Registration via Direct Superpoints Matching
arxiv(2023)
摘要
Deep neural networks endow the downsampled superpoints with highly
discriminative feature representations. Previous dominant point cloud
registration approaches match these feature representations as the first step,
e.g., using the Sinkhorn algorithm. A RANSAC-like method is then usually
adopted as a post-processing refinement to filter the outliers. Other dominant
method is to directly predict the superpoint matchings using learned MLP
layers. Both of them have drawbacks: RANSAC-based methods are computationally
intensive and prediction-based methods suffer from outputing non-existing
points in the point cloud. In this paper, we propose a straightforward and
effective baseline to find correspondences of superpoints in a global matching
manner. We employ the normalized matching scores as weights for each
correspondence, allowing us to reject the outliers and further weigh the rest
inliers when fitting the transformation matrix without relying on the
cumbersome RANSAC. Moreover, the entire model can be trained in an end-to-end
fashion, leading to better accuracy. Our simple yet effective baseline shows
comparable or even better results than state-of-the-art methods on three
datasets including ModelNet, 3DMatch, and KITTI. We do not advocate our
approach to be the solution for point cloud registration but use the
results to emphasize the role of matching strategy for point cloud
registration. The code and models are available at
https://github.com/neu-vi/Superpoints_Registration.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要