Optical flow estimation is a fundamental problem of computer vision and has many applications in the fields of robot learning and autonomous driving. This paper reveals novel geometric principles of optical flow based on the insight and detailed definition of non-occlusion. Then, two novel loss functions are proposed for the unsupervised learning of optical flow based on the geometric principles of non-occlusion. Specifically, after the occlusion part of the images are masked, the flowing process of pixel coordinate points is carefully considered and geometric constraints are conducted based on the geometric principles of optical flow. First, the optical flow vectors of neighboring pixel coordinate points in the first frame will not intersect during the pixel displacement to the second frame. Secondly, when the cluster containing adjacent four pixel coordinate points in the first frame moves to the second frame, no other pixel coordinate points will flow into the quadrilateral formed by them. According to the two geometrical constraints, the optical flow non-intersection loss and the optical flow non-blocking loss in the non-occlusion regions are proposed. Two loss functions punish the irregular and inexact optical flows in the non-occlusion regions. The experiments on datasets demonstrated that the proposed unsupervised losses of optical flow based on the geometric principles in non-occlusion regions make the estimated optical flow more refined in detail, and improve the performance of unsupervised learning of optical flow. In addition, the experiments training on synthetic data and evaluating on real data show that the generalization ability of optical flow network is improved by our proposed unsupervised approach. Our codes are open sourced at: https://github.com/IRMVLab/NccFlow.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unsupervised Learning of Optical Flow With Non-Occlusion From Geometry


    Contributors:

    Published in:

    Publication date :

    2022-11-01


    Size :

    4520823 byte




    Type of media :

    Article (Journal)


    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


    Unsupervised Occlusion-Aware Stereo Matching With Directed Disparity Smoothing

    Li, Ang / Yuan, Zejian / Ling, Yonggen et al. | IEEE | 2022


    Sparse Occlusion Detection with Optical Flow

    Ayvaci, A. / Raptis, M. / Soatto, S. | British Library Online Contents | 2012


    Visual Space Geometry Derived from Occlusion Axioms

    Petrov, A. P. / Kuzmin, L. V. | British Library Online Contents | 1996


    Unsupervised Joint Multi-Task Learning of Vision Geometry Tasks

    Jha, Prabhash Kumar / Tsanev, Doychin / Lukic, Luka | IEEE | 2021