"Transformer guided geometry model for flow-based unsupervised visual o" by Xiangyu Li, Yonghong Hou et al.
Abstract 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 auxi...
Source: uow.edu.au