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

Jakob Kruse, Carsten Rother, Uwe Schmidt; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4586-4594

Abstract


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.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Kruse_2017_ICCV,
author = {Kruse, Jakob and Rother, Carsten and Schmidt, Uwe},
title = {Learning to Push the Limits of Efficient FFT-Based Image Deconvolution},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}