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

Abstract

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.

References in corpus (4)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
• Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry