It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects. In this paper we propose a hybrid framework by interleaving a Convolutional Neural Network (CNN) and a traditional optical flow energy. We first conduct a CNN architecture using a novel learnable directional filtering layer. Such layer encodes the angle and distance similarity matrix between blur and camera motion, which is able to enhance the blur features of the camera-shake footages. The proposed CNNs are then integrated into an iterative optical flow framework, which enable the capability of modeling and solving both the blind deconvolution and the optical flow estimation problems simultaneously. Our framework is trained end-to-end on a synthetic dataset and yields competitive precision and performance against the state-of-the-art approaches.


    Access

    Download


    Export, share and cite



    Title :

    Learn to Model Blurry Motion via Directional Similarity and Filtering


    Contributors:
    Li, Wenbin (author) / Chen, Da (author) / Zhihan, Lv. (author) / Yan, Yan (author) / Cosker, Darren (author)

    Publication date :

    2018-03-01


    Remarks:

    Li , W , Chen , D , Zhihan , L , Yan , Y & Cosker , D 2018 , ' Learn to Model Blurry Motion via Directional Similarity and Filtering ' , Pattern Recognition , vol. 75 , pp. 327-338 . https://doi.org/10.1016/j.patcog.2017.04.020



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Reclaiming Blurry Data

    G. Vigil / A. Winebarger | NTIS | 2019


    Reclaiming Blurry Data

    Vigil, Genevieve / Winebarger, Amy | NTRS | 2019


    Robustness of noisy and blurry images segmentation

    Gribkov, I. V. / Koltsov, P. P. / Kotovich, N. V. et al. | British Library Online Contents | 2009


    On high-speed rail´s beaten and blurry path

    Cotey, Angela | IuD Bahn | 2011


    Study on blurry and smudgy path recognition by fuzzy neural network

    Rongben Wang, / Shouwen Ji, / Zhizhong Wang, et al. | IEEE | 2002