WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks

07/27/2020
by   Javier Cremona, et al.
0

In this work we present WGANVO, a Deep Learning based monocular Visual Odometry method. In particular, a neural network is trained to regress a pose estimate from an image pair. The training is performed using a semi-supervised approach. Unlike geometry based monocular methods, the proposed method can recover the absolute scale of the scene without neither prior knowledge nor extra information. The evaluation of the system is carried out on the well-known KITTI dataset where it is shown to work in real time and the accuracy obtained is encouraging to continue the development of Deep Learning based methods.

READ FULL TEXT
research
09/20/2017

UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning

We propose a novel monocular visual odometry (VO) system called UnDeepVO...
research
03/25/2019

Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning

Inspired by the cognitive process of humans and animals, Curriculum Lear...
research
09/21/2019

Visual Odometry Revisited: What Should Be Learnt?

In this work we present a monocular visual odometry (VO) algorithm which...
research
07/07/2021

RAM-VO: Less is more in Visual Odometry

Building vehicles capable of operating without human supervision require...
research
05/10/2023

Transformer-based model for monocular visual odometry: a video understanding approach

Estimating the camera pose given images of a single camera is a traditio...
research
03/18/2021

Deep Online Correction for Monocular Visual Odometry

In this work, we propose a novel deep online correction (DOC) framework ...
research
11/18/2016

DeepVO: A Deep Learning approach for Monocular Visual Odometry

Deep Learning based techniques have been adopted with precision to solve...

Please sign up or login with your details

Forgot password? Click here to reset