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

arXiv commentAccepted to ACM MM 2022

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Noise2Noise: Learning Image Restoration without Clean Data
• R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
• UG${}^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
• Low-Light Image Enhancement with Normalizing Flow
• Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
• Enhance Images as You Like with Unpaired Learning