Recoding Color Transfer as a Color Homography

TL;DR

This paper introduces a novel color transfer method based on color homography, enabling consistent application across images and videos, improving naturalness and reducing artifacts.

Contribution

It proposes a color homography-based decomposition of color transfer, allowing for efficient, consistent, and artifact-free color adjustments across multiple images or video frames.

Findings

The method closely approximates popular color transfer techniques.

It enables transfer application to entire videos, not just individual frames.

The approach enhances color transfer consistency and reduces artifacts.

Abstract

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.