Single-image deblurring with neural networks: A comparative survey

Jaihyun Koh; Jangho Lee; Sungroh Yoon

摘要

Neural networks (NNs) are becoming the tool of choice for sharpening blurred images. We discuss and categorize deblurring NNs. Then we evaluate seven NNs for non-blind deblurring (NBD), and seven NNs and four optimization techniques for blind deblurring (BD). To do this we use several current datasets containing pairs of sharp and blurred images, synthesized either by convolving sharp images with blur kernels or by averaging consecutive sharp images, so as to produce both uniform and non-uniform blurs. We also introduce a newly reorganized benchmark dataset in which blurred images have been classified using attributes that depend on the extent of the blur. We use this dataset to compare the effectiveness of single and multi-scale training in coping with large blurs. On NBD, NNs that use regularization with a denoising prior network outperform other denoising NNs; and NNs that use a deep image prior network outperform other deconvolution NNs. On BD, NNs outperform optimizations in signal-difference terms, but not in terms of perceptual fidelity. We found that multi-scale training helps NNs to deal with large blurs, and RNNs outperform CNNs. We also observed that GANs using a perceptual loss function produce artifacts; but also that some form of perceptual fidelity loss is required to get the best results from NNs. We contend that the domain bias of current datasets works against robustness and generality. And we discuss the potential of more sophisticated perceptual loss functions, attention techniques, and unsupervised learning.

机译：神经网络（NNS）正成为锐化模糊图像的选择的工具。我们讨论并分类DeBlurring NNS。然后，我们评估七个NNS for非盲去抑制（NBD），以及七个NNS和四个优化技术，用于盲去脱模（BD）。为此，我们使用包含具有夏普和模糊图像对的几个当前数据集，通过与模糊内核卷积清晰的图像或通过平均连续的清晰图像来合成，以产生均匀和不均匀的模糊。我们还介绍了一个新重组的基准数据集，其中模糊的图像已经使用依赖于模糊程度的属性进行分类。我们使用此数据集进行比较单一和多尺度培训的有效性，以应对大型模糊。在NBD上，NNS使用正常化与去噪的现有网络优于其他去噪NNS;使用深映像现有网络的NNS优于其他解构NN。在BD，NNS以信号差异术语优化优化，但不是在感知保真方面。我们发现多尺度培训有助于NNS处理大型模糊，并且RNNS优于CNN。我们还观察到使用感知损失功能的GAN产生伪影;但是，某些形式的感知保真度损失是从NNS获得最佳结果。我们争辩说当前数据集的域偏差适用于鲁棒性和一般性。我们讨论了更复杂的感知损失功能，注意技巧和无人监督的学习潜力。

Single-image deblurring with neural networks: A comparative survey

摘要

著录项

相关主题

期刊订阅