Aesthetic-Driven Image Enhancement by Adversarial Learning

17 Jul 2017  ·  Yubin Deng, Chen Change Loy, Xiaoou Tang ·

We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks typically involve training models in a fully-supervised manner, which require expensive annotations in the form of aligned image pairs... In contrast to these approaches, our proposed EnhanceGAN only requires weak supervision (binary labels on image aesthetic quality) and is able to learn enhancement operators for the task of aesthetic-based image enhancement. In particular, we show the effectiveness of a piecewise color enhancement module trained with weak supervision, and extend the proposed EnhanceGAN framework to learning a deep filtering-based aesthetic enhancer. The full differentiability of our image enhancement operators enables the training of EnhanceGAN in an end-to-end manner. We further demonstrate the capability of EnhanceGAN in learning aesthetic-based image cropping without any groundtruth cropping pairs. Our weakly-supervised EnhanceGAN reports competitive quantitative results on aesthetic-based color enhancement as well as automatic image cropping, and a user study confirms that our image enhancement results are on par with or even preferred over professional enhancement. read more

PDF Abstract

Results from the Paper


 Ranked #1 on Image Cropping on AVA (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Image Cropping AVA Crop Bounding Box AP 1 # 1

Methods


No methods listed for this paper. Add relevant methods here