Generative and Discriminative Learning for Distorted Image Restoration

Liquify is a common technique for image editing, which can be used for image distortion. Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task. To edit images in an efficient way, distorted images are expected to be restored automatically. This paper aims at the distorted image restoration, which is characterized by seeking the appropriate warping and completion of a distorted image. Existing methods focus on the hardware assistance or the geometric principle to solve the specific regular deformation caused by natural phenomena, but they cannot handle the irregularity and uncertainty of artificial distortion in this task. To address this issue, we propose a novel generative and discriminative learning method based on deep neural networks, which can learn various reconstruction mappings and represent complex and high-dimensional data. This method decomposes the task into a rectification stage and a refinement stage. The first stage generative network predicts the mapping from the distorted images to the rectified ones. The second stage generative network then further optimizes the perceptual quality. Since there is no available dataset or benchmark to explore this task, we create a Distorted Face Dataset (DFD) by forward distortion mapping based on CelebA dataset. Extensive experimental evaluation on the proposed benchmark and the application demonstrates that our method is an effective way for distorted image restoration.

[1]  Shang-Hong Lai,et al.  GAN-Based Day-to-Night Image Style Transfer for Nighttime Vehicle Detection , 2020, IEEE Transactions on Intelligent Transportation Systems.

[2]  Zhangyang Wang,et al.  DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Christoph H. Lampert,et al.  Document capture using stereo vision , 2004, DocEng '04.

[4]  Bernard Ghanem,et al.  Finding Tiny Faces in the Wild with Generative Adversarial Network , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Dacheng Tao,et al.  Perceptual Adversarial Networks for Image-to-Image Transformation , 2017, IEEE Transactions on Image Processing.

[6]  Ming-Hsuan Yang,et al.  Generative Face Completion , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Hongjie Li,et al.  Distorted Building Image Matching with Automatic Viewpoint Rectification and Fusion , 2019, Sensors.

[8]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[9]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Gaofeng Meng,et al.  Extraction of Virtual Baselines from Distorted Document Images Using Curvilinear Projection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Jiri Matas,et al.  DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[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]  Hao Li,et al.  High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[15]  Jianya Gong,et al.  Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image , 2019, IEEE Access.

[16]  Miloslav Hub,et al.  Automatic correction of barrel distorted images using a cascaded evolutionary estimator , 2016, Inf. Sci..

[17]  Yann LeCun,et al.  Disentangling factors of variation in deep representation using adversarial training , 2016, NIPS.

[18]  W. Brent Seales,et al.  Document restoration using 3D shape: a general deskewing algorithm for arbitrarily warped documents , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[19]  Yu Qiao,et al.  RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[21]  Minh N. Do,et al.  Semantic Image Inpainting with Deep Generative Models , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Yang Liu,et al.  Physics-Based Generative Adversarial Models for Image Restoration and Beyond , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Gaofeng Meng,et al.  Active Flattening of Curved Document Images via Two Structured Beams , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Junjun Jiang,et al.  Edge-Enhanced GAN for Remote Sensing Image Superresolution , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Masatoshi Ishikawa,et al.  3D rectification of distorted document image based on tiled rectangle fragments , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[26]  Thomas S. Huang,et al.  Generative Image Inpainting with Contextual Attention , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Jan Kautz,et al.  High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[28]  Eric Heim,et al.  Constrained Generative Adversarial Networks for Interactive Image Generation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Xu Jia,et al.  Co-Evolutionary Compression for Unpaired Image Translation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[30]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[31]  Vladlen Koltun,et al.  Photographic Image Synthesis with Cascaded Refinement Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[33]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[34]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[36]  Yu Zhang,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 an Improved Physically-based Method for Geometric Restoration of Distorted Document Images , 2007 .

[37]  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).

[38]  Ming-Hsuan Yang,et al.  Learning a Discriminative Prior for Blind Image Deblurring , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Ying Wu,et al.  Exploiting Vector Fields for Geometric Rectification of Distorted Document Images , 2018, ECCV.