Cascade Luminance and Chrominance for Image Retouching: More Like Artist

TL;DR

This paper introduces LCCNet, a two-stage neural network that mimics artist retouching by sequentially adjusting luminance and chrominance, utilizing EXIF data and hue loss to produce more vibrant images.

Contribution

The paper proposes a novel two-stage luminance-chrominance cascading network that incorporates EXIF information and hue palette loss for improved photo retouching performance.

Findings

Achieves state-of-the-art results on MIT-Adobe FiveK dataset.

Effectively mimics artist retouching behaviors.

Enhances image vibrancy and aesthetic appeal.

Abstract

Photo retouching aims to adjust the luminance, contrast, and saturation of the image to make it more human aesthetically desirable. However, artists' actions in photo retouching are difficult to quantitatively analyze. By investigating their retouching behaviors, we propose a two-stage network that brightens images first and then enriches them in the chrominance plane. Six pieces of useful information from image EXIF are picked as the network's condition input. Additionally, hue palette loss is added to make the image more vibrant. Based on the above three aspects, Luminance-Chrominance Cascading Net(LCCNet) makes the machine learning problem of mimicking artists in photo retouching more reasonable. Experiments show that our method is effective on the benchmark MIT-Adobe FiveK dataset, and achieves state-of-the-art performance for both quantitative and qualitative evaluation.