Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images

07/15/2022
by   Naishan Zheng, et al.
0

Low-light image enhancement is an inherently subjective process whose targets vary with the user's aesthetic. Motivated by this, several personalized enhancement methods have been investigated. However, the enhancement process based on user preferences in these techniques is invisible, i.e., a "black box". In this work, we propose an intelligible unsupervised personalized enhancer (iUPEnhancer) for low-light images, which establishes the correlations between the low-light and the unpaired reference images with regard to three user-friendly attributions (brightness, chromaticity, and noise). The proposed iUP-Enhancer is trained with the guidance of these correlations and the corresponding unsupervised loss functions. Rather than a "black box" process, our iUP-Enhancer presents an intelligible enhancement process with the above attributions. Extensive experiments demonstrate that the proposed algorithm produces competitive qualitative and quantitative results while maintaining excellent flexibility and scalability. This can be validated by personalization with single/multiple references, cross-attribution references, or merely adjusting parameters.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 7

page 8

research
07/03/2022

Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement

Getting rid of the fundamental limitations in fitting to the paired trai...
research
12/24/2021

Invertible Network for Unpaired Low-light Image Enhancement

Existing unpaired low-light image enhancement approaches prefer to emplo...
research
12/24/2020

LEUGAN:Low-Light Image Enhancement by Unsupervised Generative Attentional Networks

Restoring images from low-light data is a challenging problem. Most exis...
research
07/14/2022

Explaining Image Enhancement Black-Box Methods through a Path Planning Based Algorithm

Nowadays, image-to-image translation methods, are the state of the art f...
research
06/14/2021

User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning

Personalized image aesthetic assessment (PIAA) has recently become a hot...
research
08/13/2023

CLE Diffusion: Controllable Light Enhancement Diffusion Model

Low light enhancement has gained increasing importance with the rapid de...
research
01/04/2021

Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References

It is suggested that low-light image enhancement realizes one-to-many ma...

Please sign up or login with your details

Forgot password? Click here to reset