Transformer guided geometry model for flow-based unsupervised visual odometry
Transformer guided geometry model for flow-based unsupervised visual odometry
复制标题
用于基于流的无监督视觉里程计的变压器引导几何模型
DOI：
10.1007/s00521-020-05545-8
复制
发表时间：
2021-01-02
影响因子：
6
通讯作者：
Li, Wanqing
中科院分区：
文献类型：
--
作者：
Li, Xiangyu;Hou, Yonghong;Li, Wanqing
现有的无监督视觉里程计（VO）方法要么匹配成对的图像或整合的时间信息，使用递归神经网络在一个长序列的图像。它们要么不准确，训练耗时或误差累积。在本文中，我们提出了一种方法，包括两个相机姿态估计处理成对图像和一个短序列的图像，分别从信息。对于图像序列，采用类似于变换器的结构在局部时间窗口上建立几何模型，称为基于变换器的辅助姿态估计器（TAPE）。同时，提出了一种流到流姿态估计器（F2FPE），以利用成对图像之间的关系。这两个估计量通过简单而有效的训练一致性损失来约束。实证评估表明，该方法优于最先进的无监督学习的方法，由一个很大的利润，并执行监督和传统的KITTI和马拉加数据集。
Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either not accurate, time-consuming in training or error accumulative. In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images, respectively. For image sequences, a transformer-like structure is adopted to build a geometry model over a local temporal window, referred to as transformer-based auxiliary pose estimator (TAPE). Meanwhile, a flow-to-flow pose estimator (F2FPE) is proposed to exploit the relationship between pairwise images. The two estimators are constrained through a simple yet effective consistency loss in training. Empirical evaluation has shown that the proposed method outperforms the state-of-the-art unsupervised learning-based methods by a large margin and performs comparably to supervised and traditional ones on the KITTI and Malaga dataset.