Deep Generative Filter for Motion Deblurring

Removing blur caused by camera shake in images has always been a challenging problem in computer vision literature due to its ill-posed nature. Motion blur caused due to the relative motion between the camera and the object in 3D space induces a spatially varying blurring effect over the entire image. In this paper, we propose a novel deep filter based on Generative Adversarial Network (GAN) architecture integrated with global skip connection and dense architecture in order to tackle this problem. Our model, while bypassing the process of blur kernel estimation, significantly reduces the test time which is necessary for practical applications. The experiments on the benchmark datasets prove the effectiveness of the proposed method which outperforms the state-of-the-art blind deblurring algorithms both quantitatively and qualitatively.

[1]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[2]  Chuan Li,et al.  Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks , 2016, ECCV.

[3]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[4]  Tae Hyun Kim,et al.  Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[6]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[7]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Bernhard Schölkopf,et al.  Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database , 2012, ECCV.

[9]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[11]  Narendra Ahuja,et al.  A Comparative Study for Single Image Blind Deblurring , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[14]  Jean Ponce,et al.  Learning a convolutional neural network for non-uniform motion blur removal , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[17]  Ian D. Reid,et al.  From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Joan Bruna,et al.  Super-Resolution with Deep Convolutional Sufficient Statistics , 2015, ICLR.

[19]  Bernhard Schölkopf,et al.  Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake , 2010, NIPS.

[20]  Gregory Shakhnarovich,et al.  Examining the Impact of Blur on Recognition by Convolutional Networks , 2016, ArXiv.

[21]  Andrew Zisserman,et al.  Deblurring shaken and partially saturated images , 2011, ICCV Workshops.

[22]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[23]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[24]  Li Xu,et al.  Unnatural L0 Sparse Representation for Natural Image Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.