GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks

TL;DR

This paper introduces an unsupervised deep learning framework using GANs for monocular visual odometry and depth estimation from unlabelled image sequences, outperforming existing methods on standard datasets.

Contribution

It presents a novel generative adversarial network-based approach for unsupervised monocular VO and depth estimation, eliminating the need for labeled data.

Findings

Outperforms traditional and existing unsupervised VO methods

Achieves better pose estimation accuracy

Provides superior depth recovery results

Abstract

In the last decade, supervised deep learning approaches have been extensively employed in visual odometry (VO) applications, which is not feasible in environments where labelled data is not abundant. On the other hand, unsupervised deep learning approaches for localization and mapping in unknown environments from unlabelled data have received comparatively less attention in VO research. In this study, we propose a generative unsupervised learning framework that predicts 6-DoF pose camera motion and monocular depth map of the scene from unlabelled RGB image sequences, using deep convolutional Generative Adversarial Networks (GANs). We create a supervisory signal by warping view sequences and assigning the re-projection minimization to the objective loss function that is adopted in multi-view pose estimation and single-view depth generation network. Detailed quantitative and qualitative evaluations of the proposed framework on the KITTI and Cityscapes datasets show that the proposed method outperforms both existing traditional and unsupervised deep VO methods providing better results for both pose estimation and depth recovery.