The work in this paper address the problem of removing non-uniform motion blur from a single image. The motion vector for an image patch is estimated by using a convolutional neural network (CNN). All the predicted motion vectors are combined to form a dense non-uniform motion estimation map. Furthermore, a second CNN is trained to perform deblurring given a blurry image patch and the estimated motion vector. Combining the two trained networks result in a deep learning approach that can enhance degraded images. The results show that this approach can accurately determine non-uniform motion blur and restore blurred images.
Reference:
Cronje, J. 2015. Deep convolutional neural networks for dense non-uniform motion deblurring. In: The 30th International Conference on Image and Vision Computing New Zealand (IVCNZ 2015) , 23th - 24th November, Auckland, New Zealand
Cronje, J. (2015). Deep convolutional neural networks for dense non-uniform motion deblurring. IVCNZ 2015 Image and Vision Computing. http://hdl.handle.net/10204/8753
Cronje, J. "Deep convolutional neural networks for dense non-uniform motion deblurring." (2015): http://hdl.handle.net/10204/8753
Cronje J, Deep convolutional neural networks for dense non-uniform motion deblurring; IVCNZ 2015 Image and Vision Computing; 2015. http://hdl.handle.net/10204/8753 .
The 30th International Conference on Image and Vision Computing New Zealand (IVCNZ 2015), 23-24 November, Auckland, New Zealand. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website
