Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training

by   Yunxuan Wei, et al.

These days, unsupervised super-resolution (SR) has been soaring due to its practical and promising potential in real scenarios. The philosophy of off-the-shelf approaches lies in the augmentation of unpaired data, i.e. first generating synthetic low-resolution (LR) images Y^g corresponding to real-world high-resolution (HR) images X^r in the real-world LR domain Y^r, and then utilizing the pseudo pairs {Y^g, X^r} for training in a supervised manner. Unfortunately, since image translation itself is an extremely challenging task, the SR performance of these approaches are severely limited by the domain gap between generated synthetic LR images and real LR images. In this paper, we propose a novel domain-distance aware super-resolution (DASR) approach for unsupervised real-world image SR. The domain gap between training data (e.g. Y^g) and testing data (e.g. Y^r) is addressed with our domain-gap aware training and domain-distance weighted supervision strategies. Domain-gap aware training takes additional benefit from real data in the target domain while domain-distance weighted supervision brings forward the more rational use of labeled source domain data. The proposed method is validated on synthetic and real datasets and the experimental results show that DASR consistently outperforms state-of-the-art unsupervised SR approaches in generating SR outputs with more realistic and natural textures.


page 2

page 11

page 13

page 14

page 15


Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation

Most learning-based super-resolution (SR) methods aim to recover high-re...

Frequency Separation for Real-World Super-Resolution

Most of the recent literature on image super-resolution (SR) assumes the...

Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution

Although most current license plate (LP) recognition applications have b...

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

Due to the sophisticated imaging process, an identical scene captured by...

Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar

Conventional face super-resolution methods usually assume testing low-re...

SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution

In this paper, we tackle a fully unsupervised super-resolution problem, ...

Toward Super-Resolution for Appearance-Based Gaze Estimation

Gaze tracking is a valuable tool with a broad range of applications in v...

Please sign up or login with your details

Forgot password? Click here to reset