“Automatic colorization of grayscale images using multiple images on the web” by Morimoto, Taguchi and Naemura

  • ©Yuji Morimoto, Yuichi Taguchi, and Takeshi Naemura

  • ©Yuji Morimoto, Yuichi Taguchi, and Takeshi Naemura

Conference:


Type(s):


Title:

    Automatic colorization of grayscale images using multiple images on the web

Presenter(s)/Author(s):



Abstract:


    Colorization is the process of adding color to monochrome images and video. It is used to increase the visual appeal of images such as old black and white photos, classic movies, and scientific visualizations. Since colorizing grayscale images involves assigning three-dimensional (RGB) pixel values to an image whose elements are characterized by one feature (luminance) only, the colorization problem does not have a unique solution. Hence, human interaction is typically required in the colorization process. Although existing colorization methods attempt to minimize the amount of user intervention, they require users to manually sellect a similar image to the target image or input a set of color seeds for different regions of the target image. In this paper, we present an entirely automatic colorization method using multiple images collected from the Web. The method generates various and natural colorized images from an input monochrome image by using the information of the scene structure.

References:


    1. Hays, J., and Efros, A. A. 2007. Scene completion using millions of photographs. ACM Trans. Graph (SIGGRAPH 2007) 26, 3.
    2. Welsh, T., Ashikhmin, M., and Mueller, K. 2002. Transferring color to greyscale images. ACM Trans. Graph (SIGGRAPH 2002) 21, 3, 277–280.


Additional Images:

©Yuji Morimoto, Yuichi Taguchi, and Takeshi Naemura ©Yuji Morimoto, Yuichi Taguchi, and Takeshi Naemura

ACM Digital Library Publication:



Overview Page: