论文标题
施加光流估计的一致性
Imposing Consistency for Optical Flow Estimation
论文作者
论文摘要
通过代理任务施加一致性可以增强数据驱动的学习并在各种任务中实现自我划分。本文介绍了用于光流估计的新颖有效的一致性策略，这个问题是现实世界数据的标签非常具有挑战性。更具体地说，我们建议以半监督学习形式的自我监督学习和转型一致性的形式进行遮挡一致性和零强迫。我们以网络模型学会更好地描述像素级运动的方式应用这些一致性技术，同时不需要其他注释。我们证明，我们使用原始数据集和标签应用于强大的基线网络模型的一致性策略提供了进一步的改进，从而在非stleeo类别的Kitti-2015 2015场景流基准上获得了最新的结果。即使仅使用单眼图像输入，我们的方法在立体声和非STEREO类别上都达到了最佳前景精度（全部4.33％）。
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem where labels from real-world data are very challenging to derive. More specifically, we propose occlusion consistency and zero forcing in the forms of self-supervised learning and transformation consistency in the form of semi-supervised learning. We apply these consistency techniques in a way that the network model learns to describe pixel-level motions better while requiring no additional annotations. We demonstrate that our consistency strategies applied to a strong baseline network model using the original datasets and labels provide further improvements, attaining the state-of-the-art results on the KITTI-2015 scene flow benchmark in the non-stereo category. Our method achieves the best foreground accuracy (4.33% in Fl-all) over both the stereo and non-stereo categories, even though using only monocular image inputs.
