Efficient palette-based decomposition and recoloring of images via RGBXY-space geometry

摘要

We introduce an extremely scalable and efficient yet simple palette-basedimage decomposition algorithm. Given an RGB image and set of palette colors,our algorithm decomposes the image into a set of additive mixing layers,each of which corresponds to a palette color applied with varying weight.Our approach is based on the geometry of images in RGBXY-space. Thisnew geometric approach is orders of magnitude more efficient than previouswork and requires no numerical optimization. We provide an implementationof the algorithm in 48 lines of Python code. We demonstrate a real-timelayer decomposition tool in which users can interactively edit the palette toadjust the layers. After preprocessing, our algorithm can decompose 6 MPimages into layers in 20 milliseconds.