arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10983cs.CV
收藏

通过自监督长期建模学习单眼视觉里程计

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling

Virginia Tech(弗吉尼亚理工大学);NEC Labs America(NEC美国实验室);UCSD(加州大学圣迭戈分校)

Yuliang Zou, Pan Ji, Quoc-Huy Tran, Jia-Bin Huang, Manmohan Chandraker

摘要:

单目视觉里程计(VO)在帧到帧姿态估计期间遭受严重的误差累积。在本文中,我们提出了一个自监督学习方法VO与特别考虑的一致性在较长的序列。为此,我们使用具有双层卷积LSTM模块的姿势网络来建模姿势预测中的长期依赖性。我们训练网络与纯粹的自我监督的损失,包括一个周期的一致性损失,模仿几何VO中的循环闭合模块。受先前几何系统的启发,我们允许网络在训练期间超越一个小的时间窗口,通过一个新的损失,包括时间上遥远的(例如,O(100))帧。考虑到GPU内存的限制,我们提出了一个阶段式的训练机制,其中第一阶段在本地时间窗口中操作,第二阶段在给定第一阶段特征的情况下使用“全局”损失来细化姿势。我们在几个标准VO数据集上展示了具有竞争力的结果,包括KITTI和TUM RGB-D。

英文摘要:

Monocular visual odometry (VO) suffers severely from error accumulation during frame-to-frame pose estimation. In this paper, we present a self-supervised learning method for VO with special consideration for consistency over longer sequences. To this end, we model the long-term dependency in pose prediction using a pose network that features a two-layer convolutional LSTM module. We train the networks with purely self-supervised losses, including a cycle consistency loss that mimics the loop closure module in geometric VO. Inspired by prior geometric systems, we allow the networks to see beyond a small temporal window during training, through a novel a loss that incorporates temporally distant (e.g., O(100)) frames. Given GPU memory constraints, we propose a stage-wise training mechanism, where the first stage operates in a local time window and the second stage refines the poses with a "global" loss given the first stage features. We demonstrate competitive results on several standard VO datasets, including KITTI and TUM RGB-D.

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。

↑