1. [Publications](/publications) 2. Learning to Super-Resolve Blurry Face and Text Images # Learning to Super-Resolve Blurry Face and Text Images ![](/sites/default/files/styles/wide/public/publications/deblur_iccv2017_0.jpg?itok=PChpth2u) We present an algorithm to directly restore a clear high-resolution image from a blurry low-resolution input. This problem is highly ill-posed and the basic assumptions for existing super-resolution methods (requiring clear input) and deblurring methods (requiring high-resolution input) no longer hold. We focus on face and text images and adopt a generative adversarial network (GAN) to learn a category-specific prior to solve this problem. However, the basic GAN formulation does not generate realistic high-resolution images. In this work, we introduce novel training losses that help recover fine details. We also present a multi-class GAN that can process multi-class image restoration tasks, i.e., face and text images, using a single generator network. Extensive experiments demonstrate that our method performs favorably against the state-of-the-art methods on both synthetic and real-world images at a lower computational cost. ## Authors Xiangyu Xu (Tsinghua University) Deqing Sun (NVIDIA) Jinshan Pan (Nanjing University of Science & Technology) Yujin Zhang (Tsinghua University) Hanspeter Pfister (Harvard University) Ming-Hsuan Yang (University of California, Merced) ## Publication Date Tuesday, October 24, 2017 ## Published in International Conference on Computer Vision ## Research Area [Computer Vision](/research-area/computer-vision) [Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence) ## Uploaded Files [iccv2017\_gan\_super\_deblur.pdf](https://research.nvidia.com/sites/default/files/pubs/2017-10_Learning-to-Super-Resolve//iccv2017_gan_super_deblur.pdf "Open file in new window")2.12 MB ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .