Recoding Color Transfer as a Color Homography
This work addresses color transfer for image and video editing by providing a reusable model, though it is incremental as it builds on the color homography theorem.
The paper tackles the problem of color transfer in images by modeling it as a color homography, decomposing it into chromaticity shift and shading adjustment, which allows learned transfers to be applied to multiple images like video frames. Experiments show it closely approximates existing methods and enables applications such as video color grading.
Color transfer is an image editing process that adjusts the colors of a picture to match a target picture's color theme. A natural color transfer not only matches the color styles but also prevents after-transfer artifacts due to image compression, noise, and gradient smoothness change. The recently discovered color homography theorem proves that colors across a change in photometric viewing condition are related by a homography. In this paper, we propose a color-homography-based color transfer decomposition which encodes color transfer as a combination of chromaticity shift and shading adjustment. A powerful form of shading adjustment is shown to be a global shading curve by which the same shading homography can be applied elsewhere. Our experiments show that the proposed color transfer decomposition provides a very close approximation to many popular color transfer methods. The advantage of our approach is that the learned color transfer can be applied to many other images (e.g. other frames in a video), instead of a frame-to-frame basis. We demonstrate two applications for color transfer enhancement and video color grading re-application. This simple model of color transfer is also important for future color transfer algorithm design.