Quality-guided Skin Tone Enhancement for Portrait Photography

TL;DR

This paper introduces a quality-guided approach for portrait skin tone enhancement that allows continuous and controllable adjustments based on learned perceptual quality distributions, validated through subjective assessments.

Contribution

It proposes a novel quality-guided enhancement paradigm that learns image quality distributions to enable continuous, adjustable skin tone enhancement in portraits.

Findings

Effective skin tone adjustment aligned with subjective quality ratings

Model works well with limited data and fewer subjects

Demonstrates general applicability to natural images

Abstract

In recent years, learning-based color and tone enhancement methods for photos have become increasingly popular. However, most learning-based image enhancement methods just learn a mapping from one distribution to another based on one dataset, lacking the ability to adjust images continuously and controllably. It is important to enable the learning-based enhancement models to adjust an image continuously, since in many cases we may want to get a slighter or stronger enhancement effect rather than one fixed adjusted result. In this paper, we propose a quality-guided image enhancement paradigm that enables image enhancement models to learn the distribution of images with various quality ratings. By learning this distribution, image enhancement models can associate image features with their corresponding perceptual qualities, which can be used to adjust images continuously according to different quality scores. To validate the effectiveness of our proposed method, a subjective quality assessment experiment is first conducted, focusing on skin tone adjustment in portrait photography. Guided by the subjective quality ratings obtained from this experiment, our method can adjust the skin tone corresponding to different quality requirements. Furthermore, an experiment conducted on 10 natural raw images corroborates the effectiveness of our model in situations with fewer subjects and fewer shots, and also demonstrates its general applicability to natural images. Our project page is https://github.com/IntMeGroup/quality-guided-enhancement .