Learning to Super-Resolve Blurry Face and Text Images
Abstract
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 22, 2017
- Accession Number
- AD1165726
Entities
People
- Deqing Sun
- Hanspeter Pfister
- Jinshan Pan
- Ming-Hsuan Yang
- Xiangyu Xu
- Yujin Zhang
Organizations
- Harvard University
- Nanjing University of Science and Technology
- Nvidia
- Tsinghua University
- University of California