Details

Autor(en) / Beteiligte

• Xiangyu Xu
• Deqing Sun
• Jinshan Pan
• Yujin Zhang
• Pfister, Hanspeter
• Ming-Hsuan Yang

Titel

Learning to Super-Resolve Blurry Face and Text Images

Ist Teil von

• 2017 IEEE International Conference on Computer Vision (ICCV), 2017, p.251-260

Ort / Verlag

IEEE

Erscheinungsjahr

2017

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• We present an algorithm to directly restore a clear highresolution 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.