Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Françani, André O., Maximo, Marcos R. O. A.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911761026777088
author Françani, André O.
Maximo, Marcos R. O. A.
author_facet Françani, André O.
Maximo, Marcos R. O. A.
contents Deep learning algorithms have driven expressive progress in many complex tasks. The loss function is a core component of deep learning techniques, guiding the learning process of neural networks. This paper contributes by introducing a consistency loss for visual odometry with deep learning-based approaches. The motion consistency loss explores repeated motions that appear in consecutive overlapped video clips. Experimental results show that our approach increased the performance of a model on the KITTI odometry benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10857
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning
Françani, André O.
Maximo, Marcos R. O. A.
Computer Vision and Pattern Recognition
Robotics
68T45 68T07
Deep learning algorithms have driven expressive progress in many complex tasks. The loss function is a core component of deep learning techniques, guiding the learning process of neural networks. This paper contributes by introducing a consistency loss for visual odometry with deep learning-based approaches. The motion consistency loss explores repeated motions that appear in consecutive overlapped video clips. Experimental results show that our approach increased the performance of a model on the KITTI odometry benchmark.
title Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning
topic Computer Vision and Pattern Recognition
Robotics
68T45 68T07
url https://arxiv.org/abs/2401.10857