DeepAI AI Chat
Log In Sign Up

UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning

by   Ruihao Li, et al.
University of Essex
Heriot-Watt University

We propose a novel monocular visual odometry (VO) system called UnDeepVO in this paper. UnDeepVO is able to estimate the 6-DoF pose of a monocular camera and the depth of its view by using deep neural networks. There are two salient features of the proposed UnDeepVO: one is the unsupervised deep learning scheme, and the other is the absolute scale recovery. Specifically, we train UnDeepVO by using stereo image pairs to recover the scale but test it by using consecutive monocular images. Thus, UnDeepVO is a monocular system. The loss function defined for training the networks is based on spatial and temporal dense information. A system overview is shown in Fig. 1. The experiments on KITTI dataset show our UnDeepVO outperforms other monocular VO methods in terms of pose accuracy.


page 1

page 2

page 3

page 6


WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks

In this work we present WGANVO, a Deep Learning based monocular Visual O...

Pose Graph Optimization for Unsupervised Monocular Visual Odometry

Unsupervised Learning based monocular visual odometry (VO) has lately dr...

A Deeper Insight into the UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation

This paper presents an unsupervised deep learning framework called UnDEM...

MagicVO: End-to-End Monocular Visual Odometry through Deep Bi-directional Recurrent Convolutional Neural Network

This paper proposes a new framework to solve the problem of monocular vi...

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Unsupervised learning for monocular camera motion and 3D scene understan...

Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency

Previous works have shown that adversarial learning can be used for unsu...

Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints

Monocular depth inference has gained tremendous attention from researche...