2021 · 129 citations · 32 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine VisionDeep LearningDigital Image ProcessingImage ProcessingImage RestorationVisual Receptive FieldsComplex NetworksDeblurringImage DeblurringReceptive Field EncodingReceptive Field ExpansionSamplingTexture LossWavelet Transform
Image deblurring is a classical computer vision problem that aims to recover a sharp image from a blurred image. To solve this problem, existing methods apply the Encode-Decode architecture to design the complex networks to make a good performance. However, most of these methods use repeated up-sampling and down-sampling structures to expand the receptive field, which results in texture information loss during the sampling process and some of them design the multiple stages that lead to difficulties with convergence. Therefore, our model uses dilated convolution to enable the obtainment of the large receptive field with high spatial resolution. Through making full use of the different receptive fields, our method can achieve better performance. On this basis, we reduce the number of up-sampling and down-sampling and design a simple network structure. Besides, we propose a novel module using the wavelet transform, which effectively helps the network to recover clear high-frequency texture details. Qualitative and quantitative evaluations of real and synthetic datasets show that our deblurring method is comparable to existing algorithms in terms of performance with much lower training requirements. The source code and pre-trained models are available at https://github.com/FlyEgle/SDWNet.
32
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations
Decoupled Weight Decay Regularization
Ilya Loshchilov, Frank Hutter · arXiv (Cornell University) · 2017 · 9.1K citations · Full text
Loss Functions for Image Restoration With Neural Networks
Hang Zhao, Orazio Gallo, Iuri Frosio et al. · IEEE Transactions on Computational Imaging · 2016 · 2.6K citations
Multi-Stage Progressive Image Restoration
Syed Waqas Zamir, Aditya Arora, Salman Khan et al. · 2021 · 1.9K citations