Cascade Luminance and Chrominance for Image Retouching: More Like Artist
This work addresses the challenge of quantitatively analyzing and replicating artists' aesthetic adjustments in photo retouching, which is incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of mimicking artists' photo retouching behaviors by proposing a two-stage network that adjusts luminance and chrominance, achieving state-of-the-art performance on the MIT-Adobe FiveK dataset.
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.