Deep Patch Visual Odometry

08/08/2022
by   Zachary Teed, et al.
0

We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO). DPVO is accurate and robust while running at 2x-5x real-time speeds on a single RTX-3090 GPU using only 4GB of memory. We perform evaluation on standard benchmarks and outperform all prior work (classical or learned) in both accuracy and speed. Code is available at https://github.com/princeton-vl/DPVO.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/11/2018

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

Despite learning based methods showing promising results in single view ...
03/15/2022

DSOL: A Fast Direct Sparse Odometry Scheme

In this paper, we describe Direct Sparse Odometry Lite (DSOL), an improv...
09/20/2016

Reducing Drift in Visual Odometry by Inferring Sun Direction Using a Bayesian Convolutional Neural Network

We present a method to incorporate global orientation information from t...
07/27/2020

WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks

In this work we present WGANVO, a Deep Learning based monocular Visual O...
07/29/2020

Simultaneously Learning Corrections and Error Models for Geometry-based Visual Odometry Methods

This paper fosters the idea that deep learning methods can be used to co...
10/04/2021

LLOL: Low-Latency Odometry for Spinning Lidars

In this paper, we present a low-latency odometry system designed for spi...
07/07/2021

RAM-VO: Less is more in Visual Odometry

Building vehicles capable of operating without human supervision require...

Code Repositories