DeepAI AI Chat
Log In Sign Up

Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software

by   Satoshi Kosugi, et al.
The University of Tokyo

This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. Our method is based on generative adversarial networks (GANs), but instead of simply generating images with a neural network, we enhance images utilizing image editing software such as Adobe Photoshop for the following three benefits: enhanced images have no artifacts, the same enhancement can be applied to larger images, and the enhancement is interpretable. To incorporate image editing software into a GAN, we propose a reinforcement learning framework where the generator works as the agent that selects the software's parameters and is rewarded when it fools the discriminator. Our framework can use high-quality non-differentiable filters present in image editing software, which enables image enhancement with high performance. We apply the proposed method to two unpaired image enhancement tasks: photo enhancement and face beautification. Our experimental results demonstrate that the proposed method achieves better performance, compared to the performances of the state-of-the-art methods based on unpaired learning.


page 3

page 5

page 6

page 7


A Generative Adversarial Approach with Residual Learning for Dust and Scratches Artifacts Removal

Retouching can significantly elevate the visual appeal of photos, but ma...

Controllable Image Enhancement

Editing flat-looking images into stunning photographs requires skill and...

TreEnhance: An Automatic Tree-Search Based Method for Low-Light Image Enhancement

In this paper we present TreEnhance, an automatic method for low-light i...

Flexible Example-based Image Enhancement with Task Adaptive Global Feature Self-Guided Network

We propose the first practical multitask image enhancement network, that...

PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing

This paper tackles a new problem setting: reinforcement learning with pi...

Does V-NIR based Image Enhancement Come with Better Features?

Image enhancement using the visible (V) and near-infrared (NIR) usually ...

Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement

This paper introduces a divide-and-conquer inspired adversarial learning...

Code Repositories