基于注意力深度学习的单目视觉里程计运动一致性损失
Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning
AI总结：
本文面向基于深度学习的视觉里程计，提出利用连续重叠视频片段中重复运动的运动一致性损失，并在 KITTI 基准上验证其可提升模型性能。
摘要：
深度学习算法已在许多复杂任务中推动了显著进展。损失函数是深度学习技术的核心组成部分，用于引导神经网络的学习过程。本文的贡献在于为基于深度学习的视觉里程计方法引入了一种一致性损失。该运动一致性损失利用连续重叠视频片段中出现的重复运动。实验结果表明，该方法提升了模型在 KITTI 里程计基准上的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
