Hand-held Video Deblurring via
Efficient Fourier Aggregation

IEEE Transactions on Computational Imaging

Mauricio Delbracio  and   Guillermo Sapiro

Department of Electrical and Computer Engineering
Duke University


Videos captured with hand-held cameras often suffer from a significant amount of blur, mainly caused by the inevitable natural tremor of the photographer's hand. In this work, we present an algorithm that removes this type of blur in videos by combining information in the Fourier domain from nearby frames. The dynamic nature of typical videos with the presence of moving objects makes this problem extremely challenging, in particular when low complexity is needed. Given an input video frame, we first create a consistent registered version of temporally adjacent frames. Then, the set of consistently registered frames is block-wise fused in the Fourier domain with weights depending on the Fourier spectrum magnitude. The method is motivated from the physiological fact that camera shake blur has a random nature and therefore, nearby video frames are generally blurred differently. Experiments with videos recorded in the wild, along with extensive comparisons, show that the proposed algorithm achieves state-of-the-art results while at the same time being much faster than its competitors.

Additional Material

    author = {Delbracio, Mauricio and Sapiro, Guillermo},
    title = {{Hand-Held Video Deblurring Via Efficient Fourier Aggregation}},
    journal = {Computational Imaging, IEEE Transactions on},
    volume = {1},
    number = {4},
    month = {Dec},
    year = {2015},
    issn = {2333-9403},
    pages = {270-283},
    doi = {10.1109/TCI.2015.2501245}

last modified: 14 Dec 2015
Valid XHTML 1.0 Strict