Learning Blind Motion Deblurring

Patrick Wieschollek, Michael Hirsch, Bernhard Scholkopf, Hendrik P. A. Lensch; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 231-240

As handheld video cameras are now commonplace and available in every smartphone images and videos can be recorded almost everywhere at any time. However, taking a quick shot frequently ends up in a blurry result due to unwanted camera shake during recording or moving objects in the scene. Removing these artifacts from the blurry recordings is a highly ill-posed problem as neither the sharp image nor the motion blur is known. Propagating information between multiple consecutive blurry observations can help to restore the desired sharp image or video. Solutions for blind deconvolution based on neural networks rely on a massive amount of ground-truth data which was difficult to acquire. In this work, we propose an efficient approach to produce a significant amount of realistic training data and introduce a novel recurrent network architecture to deblur frames, which can efficiently handle arbitrary spatial and temporal input sizes.