MotionHint: 基于运动约束的自监督单目视觉里程计
MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints
AI总结：
MotionHint通过引入运动约束模型，提升单目视觉里程计的精度，减少ATE误差达28.73%
摘要：
我们提出了一种名为MotionHint的新自监督算法，用于单目视觉里程计（VO），该算法考虑了运动约束。我们方法的关键在于使用适当的运动模型，帮助现有的自监督单目VO（SSM-VO）算法克服其自监督损失函数中局部极小值的问题。运动模型通过一个名为PPnet的神经网络表达。它被训练以粗略预测相机的下一个姿态以及该预测的不确定性。我们的自监督方法结合了原始损失和运动损失，后者是预测与生成的自体运动之间的加权差。以两个现有的SSM-VO系统作为基线，我们在标准的KITTI基准上评估了我们的MotionHint算法。实验结果表明，我们的MotionHint算法可以轻松应用于现有的开源最先进SSM-VO系统，通过减少最终ATE的幅度达28.73%来显著提高性能。
英文摘要：
We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues related to the local minima within their self-supervised loss functions. The motion model is expressed with a neural network named PPnet. It is trained to coarsely predict the next pose of the camera and the uncertainty of this prediction. Our self-supervised approach combines the original loss and the motion loss, which is the weighted difference between the prediction and the generated ego-motion. Taking two existing SSM-VO systems as our baseline, we evaluate our MotionHint algorithm on the standard KITTI benchmark. Experimental results show that our MotionHint algorithm can be easily applied to existing open-sourced state-of-the-art SSM-VO systems to greatly improve the performance by reducing the resulting ATE by up to 28.73%.
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。
