通过权重共享聚合利用隐式刚性约束以从点云估计场景流
Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds
AI总结：
本文提出一种隐式利用刚性约束的权重共享聚合(WSA)方法和形变度模块，并将其集成到PointPWC-Net构建WSAFlowNet，在FlyingThings3D和KITTI数据集上大幅提升了场景流估计性能。
摘要：
场景流估计从点云预测场景点的3D运动，是自动驾驶和许多其他3D视觉应用中的核心任务。现有方法要么由于忽略刚体运动一致性而遭受结构失真，要么需要显式位姿估计和3D物体分割。估计位姿和分割物体的误差会导致不准确的刚性约束，进而误导场景流估计。在本文中，我们提出了一种新颖的权重共享聚合（WSA）方法，用于特征和场景流上采样。WSA不依赖于估计的位姿和分割的物体，能够隐式地强制执行刚性约束，以避免场景流估计中的结构失真。为了进一步利用几何信息并保留局部结构，我们设计了一个形变度模块，旨在保持局部区域不变性。我们修改了PointPWC-Net，并将所提出的WSA和形变度模块集成到增强的PointPWC-Net中，以构建一个端到端的场景流估计网络，称为WSAFlowNet。在FlyingThings3D和KITTI数据集上的大量实验结果表明，我们的WSAFlowNet实现了最先进的性能，并以较大优势超越了以前的方法。我们将在https://github.com/wangyunlhr/WSAFlowNet.git发布源代码。
英文摘要：
Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications. Existing methods either suffer from structure distortion due to ignorance of rigid motion consistency or require explicit pose estimation and 3D object segmentation. Errors of estimated poses and segmented objects would yield inaccurate rigidity constraints and in turn mislead scene flow estimation. In this paper, we propose a novel weight-sharing aggregation (WSA) method for feature and scene flow up-sampling. WSA does not rely on estimated poses and segmented objects, and can implicitly enforce rigidity constraints to avoid structure distortion in scene flow estimation. To further exploit geometric information and preserve local structure, we design a deformation degree module aim to keep the local region invariance. We modify the PointPWC-Net and integrate the proposed WSA and deformation degree module into the enhanced PointPWC-Net to derive an end-to-end scene flow estimation network, called WSAFlowNet. Extensive experimental results on the FlyingThings3D and KITTI datasets demonstrate that our WSAFlowNet achieves the state-of-the-art performance and outperforms previous methods by a large margin. We will release the source code at https://github.com/wangyunlhr/WSAFlowNet.git.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
