2020/06/08 by Xiaobin Wei, Wei, Xiaobin, Jianjiang Feng +3
Computer Science · Engineering · #Advanced Vision and Imaging #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Deep learning #Exploit #FOS: Computer and information sciences #Monocular #Motion (physics) #Optical measurement and interference techniques #Pattern recognition (psychology) #Process (computing) #Robotics and Sensor-Based Localization #Segmentation #Semantics (computer science) #Unsupervised learning #cs.CV
paper · pdf · doi:10.48550/arxiv.2006.04371
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/06/08 · openalex publication_date 2020/06/08 · arxiv updated 2020/06/09 · openalex created_date 2020/06/12 · openalex updated_date 2026/07/28
We propose a semantics-driven unsupervised learning approach for monocular depth and ego-motion estimation from videos in this paper. Recent unsupervised learning methods employ photometric errors between synthetic view and actual image as a supervision signal for training. In our method, we exploit semantic segmentation information to mitigate the effects of dynamic objects and occlusions in the scene, and to improve depth prediction performance by considering the correlation between depth and semantics. To avoid costly labeling process, we use noisy semantic segmentation results obtained by a pre-trained semantic segmentation network. In addition, we minimize the position error between the corresponding points of adjacent frames to utilize 3D spatial information. Experimental results on the KITTI dataset show that our method achieves good performance in both depth and ego-motion estimation tasks.