arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.09103cs.CVcs.RO
收藏

超越光度损失的自监督自我运动估计

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

Department of Computer Science and Engineering, Hong Kong University of Science and Technology(香港科技大学计算机科学与工程学系);Tencent YouTu Lab, Shenzhen(腾讯优图实验室(深圳));Everest Innovation Technology (Altizure), Hong Kong(Everest Innovation Technology(Altizure),香港)

Tianwei Shen, Zixin Luo, Lei Zhou, Hanyu Deng, Runze Zhang, Tian Fang, Long Quan

摘要:

精确的相对位姿是视觉里程计(VO)和同时定位与地图构建(SLAM)的关键组成部分之一。最近,联合优化相对姿态和目标图像深度的自监督学习框架引起了社会的关注。以前的工作依赖于相邻帧之间的深度和姿态产生的光度误差,其中包含由于反射表面和遮挡而导致的真实场景下的大的系统误差。在本文中,我们通过在自监督框架中引入对极几何约束的匹配损失来弥合几何损失和光度损失之间的差距。在KITTI数据集上进行评估,我们的方法比最先进的无监督自我运动估计方法有很大的优势。代码和数据可在https://github.com/hlzz/DeepMatchVO上获得。

英文摘要:

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM). Recently, the self-supervised learning framework that jointly optimizes the relative pose and target image depth has attracted the attention of the community. Previous works rely on the photometric error generated from depths and poses between adjacent frames, which contains large systematic error under realistic scenes due to reflective surfaces and occlusions. In this paper, we bridge the gap between geometric loss and photometric loss by introducing the matching loss constrained by epipolar geometry in a self-supervised framework. Evaluated on the KITTI dataset, our method outperforms the state-of-the-art unsupervised ego-motion estimation methods by a large margin. The code and data are available at https://github.com/hlzz/DeepMatchVO.

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。

↑