Image recoloring for home scene

Abstract

Indoor home scene coloring technology is a hot topic for home design, helping users make home coloring decisions. Image based home scene coloring is preferable for e-commerce customers since it only requires users to describe coloring expectations or manipulate colors through images, which is intuitive and inexpensive. In contrast, if home scene coloring is performed based on 3D scenes, the process becomes expensive due to the high cost and time in obtaining 3D models and constructing 3D scenes. To realize image based home scene coloring, our framework can extract the coloring of individual furniture together with their relationship. This allows us to formulate the color structure of the home scene, serving as the basis for color migration. Our work is challenging since it is not intuitive to identify the coloring of furniture and their parts as well as the coloring relationship among furniture. This paper presents a new color migration framework for home scenes. We first extract local coloring from a home scene image forming a regional color table. We then generate a matching color table from a template image based on its color structure. Finally we transform the target image coloring based on the matching color table and well maintain the boundary transitions among image regions. We also introduce an interactive operation to guide such transformation. Experiments show our framework can produce good results meeting human visual expectations.