Learning to Push the Limits of Efficient FFT-Based Image Deconvolution

TitleLearning to Push the Limits of Efficient FFT-Based Image Deconvolution
Publication TypeConference Paper
Year of Publication2017
AuthorsKruse, J, Rother, C, Schmidt, U
Conference NameProceedings of the IEEE International Conference on Computer Vision
ISBN Number9781538610329

This work addresses the task of non-blind image deconvolution. Motivated to keep up with the constant increase in image size, with megapixel images becoming the norm, we aim at pushing the limits of efficient FFT-based techniques. Based on an analysis of traditional and more recent learning-based methods, we generalize existing discriminative approaches by using more powerful regularization, based on convolutional neural networks. Additionally, we propose a simple, yet effective, boundary adjustment method that alleviates the problematic circular convolution assumption, which is necessary for FFT-based deconvolution. We evaluate our approach on two common non-blind deconvolution benchmarks and achieve state-of-the-art results even when including methods which are computationally considerably more expensive.

Citation KeyKruse2017