EMR-MSF：利用自运动刚性的自监督循环单目场景流
EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity
AI总结：
提出EMR-MSF自监督单目场景流模型，利用自运动刚性和软掩码过滤动态区域，结合多种损失与训练策略，在KITTI基准上SF-all指标提升44%，性能媲美监督方法。
摘要：
自监督单目场景流估计旨在从两幅时间上连续的单目图像中同时理解三维结构和三维运动，因其传感器设置简单且经济而受到越来越多的关注。然而，当前方法的准确性受制于网络架构效率较低以及缺乏用于正则化的运动刚性的瓶颈。在本文中，我们借鉴监督学习范畴下的网络架构设计优势，提出了一种名为EMR-MSF的优越模型。我们进一步通过精心构建的自运动聚合模块施加显式且鲁棒的几何约束，其中提出了一个刚性软掩码，用于滤除动态区域，从而利用静态区域进行稳定的自运动估计。此外，我们提出了运动一致性损失和掩码正则化损失，以充分利用静态区域。我们整合了几种高效的训练策略，包括梯度分离技术和增强的视图合成过程，以获得更好的性能。我们提出的方法大幅优于先前的自监督方法，并赶上了监督方法的性能。在KITTI场景流基准上，我们的方法将最先进的自监督单目方法的SF-all指标提升了44%，并在包括深度和视觉里程计在内的子任务中，相较于其他自监督单任务或多任务方法展现了优越的性能。
英文摘要：
Self-supervised monocular scene flow estimation, aiming to understand both 3D structures and 3D motions from two temporally consecutive monocular images, has received increasing attention for its simple and economical sensor setup. However, the accuracy of current methods suffers from the bottleneck of less-efficient network architecture and lack of motion rigidity for regularization. In this paper, we propose a superior model named EMR-MSF by borrowing the advantages of network architecture design under the scope of supervised learning. We further impose explicit and robust geometric constraints with an elaborately constructed ego-motion aggregation module where a rigidity soft mask is proposed to filter out dynamic regions for stable ego-motion estimation using static regions. Moreover, we propose a motion consistency loss along with a mask regularization loss to fully exploit static regions. Several efficient training strategies are integrated including a gradient detachment technique and an enhanced view synthesis process for better performance. Our proposed method outperforms the previous self-supervised works by a large margin and catches up to the performance of supervised methods. On the KITTI scene flow benchmark, our approach improves the SF-all metric of the state-of-the-art self-supervised monocular method by 44% and demonstrates superior performance across sub-tasks including depth and visual odometry, amongst other self-supervised single-task or multi-task methods.
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。
