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

TL;DR

This paper introduces an unsupervised, personalized low-light image enhancer that makes the enhancement process transparent by linking it to user-friendly attributes like brightness, chromaticity, and noise, offering flexible and scalable customization.

Contribution

It proposes an intelligible unsupervised framework for personalized low-light enhancement that explicitly models user preferences through interpretable attributions, unlike previous black-box methods.

Findings

Produces competitive qualitative results

Maintains high flexibility and scalability

Allows personalization with various reference images

Abstract

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.