论文标题
通过概率密度函数的对齐方式进行自我监督的强大场景流量估计
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions
论文作者
论文摘要
在本文中，我们为一对连续的点云提供了一种新的自我监督场景流估计方法。我们方法的关键思想是使用高斯混合模型表示离散点云是连续概率密度函数。因此，场景流量估计转换为从概率密度函数的比对恢复运动的问题，我们使用经典的Cauchy-Schwarz差异的封闭形式表达来实现。与现有的基于最近的邻居的方法不同，我们提出的方法在点云之间建立了柔软的和隐式点的对应关系，并在存在缺失的对应关系和离群值的情况下生成更健壮和准确的场景流。全面的实验表明，我们的方法在倒角距离和地球推动者在现实世界环境中的距离取得了明显的收益，并在FlyingThings3D和Kitti上的自我监督学习方法中实现了最先进的表现，甚至超过了一些具有地面真理注释的监督方法。
In this paper, we present a new self-supervised scene flow estimation approach for a pair of consecutive point clouds. The key idea of our approach is to represent discrete point clouds as continuous probability density functions using Gaussian mixture models. Scene flow estimation is therefore converted into the problem of recovering motion from the alignment of probability density functions, which we achieve using a closed-form expression of the classic Cauchy-Schwarz divergence. Unlike existing nearest-neighbor-based approaches that use hard pairwise correspondences, our proposed approach establishes soft and implicit point correspondences between point clouds and generates more robust and accurate scene flow in the presence of missing correspondences and outliers. Comprehensive experiments show that our method makes noticeable gains over the Chamfer Distance and the Earth Mover's Distance in real-world environments and achieves state-of-the-art performance among self-supervised learning methods on FlyingThings3D and KITTI, even outperforming some supervised methods with ground truth annotations.
