期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 12758-12767出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.01257
关键词
-
资金
- Argo AI
- CMU Argo AI Center for Autonomous Vehicle Research
Recent examination of learning-based point cloud registration methods revealed poor performance in mismatched conditions, suggesting the use of classical non-learning methods or hybrid learning methods. PointNetLK, with the inclusion of an analytical Jacobian, showed significant improvement in generalization properties.
We address the generalization ability of recent learning-based point cloud registration methods. Despite their success, these approaches tend to have poor performance when applied to mismatched conditions that are not well-represented in the training set, such as unseen object categories, different complex scenes, or unknown depth sensors. In these circumstances, it has often been better to rely on classical non-learning methods (e.g., Iterative Closest Point), which have better generalization ability. Hybrid learning methods, that use learning for predicting point correspondences and then a deterministic step for alignment, have offered some respite, but are still limited in their generalization abilities. We revisit a recent innovation-PointNetLK [1]-and show that the inclusion of an analytical Jacobian can exhibit remarkable generalization properties while reaping the inherent fidelity benefits of a learning framework. Our approach not only outperforms the state-of-the-art in mismatched conditions but also produces results competitive with current learning methods when operating on real-world test data close to the training set.
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