论文标题
通过方向估计对点云进行自我监督的学习
Self-supervised Learning of Point Clouds via Orientation Estimation
论文作者
论文摘要
点云提供了3D形状的紧凑而有效的表示。尽管深度神经网络在点云学习任务上取得了令人印象深刻的结果，但它们需要大量的手动标记数据，这可能是昂贵且耗时的收集数据。在本文中，我们利用3D自我求职者在标签较少的点云上学习下游任务。点云可以无限多种方式旋转，这为自我设计提供了丰富的无标签源。我们考虑预测旋转的辅助任务，这些任务又导致了其他任务（例如形状分类和3D KePoint预测）的有用功能。使用Shapenet和ModelNet上的实验，我们证明我们的方法的表现优于最新方法。此外，我们的模型学到的功能与其他自我监督方法相辅相成，并将它们结合起来会进一步提高性能。
Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly and time-consuming to collect. In this paper, we leverage 3D self-supervision for learning downstream tasks on point clouds with fewer labels. A point cloud can be rotated in infinitely many ways, which provides a rich label-free source for self-supervision. We consider the auxiliary task of predicting rotations that in turn leads to useful features for other tasks such as shape classification and 3D keypoint prediction. Using experiments on ShapeNet and ModelNet, we demonstrate that our approach outperforms the state-of-the-art. Moreover, features learned by our model are complementary to other self-supervised methods and combining them leads to further performance improvement.
