arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09115cs.CV
收藏

光度不一致条件下深度和运动的自监督学习

Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency

HKUST(香港科技大学);Tsinghua University(清华大学);Altizure

Tianwei Shen, Lei Zhou, Zixin Luo, Yao Yao, Shiwei Li, Jiahui Zhang, Tian Fang, Long Quan

摘要:

通过使用附近帧的光度一致性,来自单目序列的深度和姿态的自监督学习提供了一种有吸引力的解决方案,因为它对地面实况数据的依赖要小得多。在本文中,我们解决的问题时,以前的假设的自我监督的方法被违反,由于现实世界的场景的动态性。与将噪声作为不确定性处理不同,我们的核心思想是在时间图像序列中加入更鲁棒的几何量并加强内部一致性。如在常用的基准数据集上所示,所提出的方法在不增加推理开销的情况下,大大改进了单目图像序列的深度和相对姿态估计的最新方法。

英文摘要:

The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data. In this paper, we address the issue when previous assumptions of the self-supervised approaches are violated due to the dynamic nature of real-world scenes. Different from handling the noise as uncertainty, our key idea is to incorporate more robust geometric quantities and enforce internal consistency in the temporal image sequence. As demonstrated on commonly used benchmark datasets, the proposed method substantially improves the state-of-the-art methods on both depth and relative pose estimation for monocular image sequences, without adding inference overhead.

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。

↑