NamedCurves: Learned Image Enhancement via Color Naming
This work addresses image enhancement for users seeking intuitive color-based editing, but it is incremental as it builds on existing learning-based methods with a focus on color naming.
The paper tackled the problem of image enhancement by learning to adjust images based on named colors, such as 'blue' or 'green', using tone curves and attention-based fusion, and demonstrated effectiveness with notable improvements on the Adobe 5K and PPR10K datasets.
A popular method for enhancing images involves learning the style of a professional photo editor using pairs of training images comprised of the original input with the editor-enhanced version. When manipulating images, many editing tools offer a feature that allows the user to manipulate a limited selection of familiar colors. Editing by color name allows easy adjustment of elements like the "blue" of the sky or the "green" of trees. Inspired by this approach to color manipulation, we propose NamedCurves, a learning-based image enhancement technique that separates the image into a small set of named colors. Our method learns to globally adjust the image for each specific named color via tone curves and then combines the images using an attention-based fusion mechanism to mimic spatial editing. We demonstrate the effectiveness of our method against several competing methods on the well-known Adobe 5K dataset and the PPR10K dataset, showing notable improvements.