Unsupervised deep learning methods have demonstrated an impressive performance for understanding the structure of 3D scene from videos. These data-based learning methods are able to learn the tasks, such as depth, ego-motion, and optical flow estimation. In this paper, we propose a novel unsupervised deep learning method to jointly estimate scene depth, camera ego-motion, and optical flow from stereo images. Consecutive stereo images are used to train the system. After training stage, the system is able to estimate dense depth map, camera 6D pose, and optical flow by using a sequence of monocular images. No labelled data set is required for training. The supervision signals for training three deep neural networks of the system come from various forms of image warping. Due to the use of optical flow, the impact caused by occlusions and moving objects on the estimation results is alleviated. Experiments on the KITTI and Cityscapes datasets show that the proposed system demonstrates a better performance in terms of accuracy in depth, ego-motion, and optical flow estimation.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unsupervised Deep Learning of Depth, Ego-Motion, and Optical Flow from Stereo Images


    Contributors:
    Yang, Delong (author) / Luo, Zhaohui (author) / Shang, Peng (author) / Hu, Zhigang (author)


    Publication date :

    2021-08-09


    Size :

    2248286 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Unsupervised Learning of Depth, Optical Flow and Pose With Occlusion From 3D Geometry

    Wang, Guangming / Zhang, Chi / Wang, Hesheng et al. | IEEE | 2022


    Depth map estimation with stereo images

    European Patent Office | 2017

    Free access

    Unsupervised Multi-Spectrum Stereo Depth Estimation for All-Day Vision

    Guo, Yubin / Kong, Hui / Gu, Shuo | IEEE | 2024


    Estimation of depth and 3D motion parameter of moving object with multiple stereo images

    Yi, J.-W. / Oh, J.-H. | British Library Online Contents | 1996


    UNSUPERVISED MOTION LEARNING FROM A MOVING PLATFORM

    Romero-Cano, V. / Nieto, J. / Agamennoni, G. et al. | British Library Conference Proceedings | 2013