Fast Image and Video Colorization Using Chrominance Blending Export

@article{citeulike:616999, abstract = {Colorization, the task of coloring a grayscale image or video, involves assigning from the single dimension of intensity or luminance a quantity that varies in three dimensions, such as red, green, and blue channels. Mapping between intensity and color is, therefore, not unique, and colorization is ambiguous in nature and requires some amount of human interaction or external information. A computationally simple, yet effective, approach of colorization is presented in this paper. The method is fast and it can be conveniently used \&\#8220;on the fly,\&\#8221; permitting the user to interactively get the desired results promptly after providing a reduced set of chrominance scribbles. Based on the concepts of luminance-weighted chrominance blending and fast intrinsic distance computations, high-quality colorization results for still images and video are obtained at a fraction of the complexity and computational cost of previously reported techniques. Possible extensions of the algorithm introduced here included the capability of changing the colors of an existing color image or video, as well as changing the underlying luminance, and many other special effects demonstrated here.}, author = {Yatziv, L. and Sapiro, G.}, citeulike-article-id = {616999}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TIP.2005.864231}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1621234}, doi = {10.1109/TIP.2005.864231}, journal = {Image Processing, IEEE Transactions on}, keywords = {blending, colorization, fast, scribbles}, number = {5}, pages = {1120--1129}, posted-at = {2007-12-10 17:43:45}, priority = {5}, title = {Fast Image and Video Colorization Using Chrominance Blending}, url = {http://dx.doi.org/10.1109/TIP.2005.864231}, volume = {15}, year = {2006} }

TY - JOUR ID - citeulike:616999 L3 - citeulike-article-id:616999 N2 - Colorization, the task of coloring a grayscale image or video, involves assigning from the single dimension of intensity or luminance a quantity that varies in three dimensions, such as red, green, and blue channels. Mapping between intensity and color is, therefore, not unique, and colorization is ambiguous in nature and requires some amount of human interaction or external information. A computationally simple, yet effective, approach of colorization is presented in this paper. The method is fast and it can be conveniently used “on the fly,” permitting the user to interactively get the desired results promptly after providing a reduced set of chrominance scribbles. Based on the concepts of luminance-weighted chrominance blending and fast intrinsic distance computations, high-quality colorization results for still images and video are obtained at a fraction of the complexity and computational cost of previously reported techniques. Possible extensions of the algorithm introduced here included the capability of changing the colors of an existing color image or video, as well as changing the underlying luminance, and many other special effects demonstrated here. IS - 5 JF - Image Processing, IEEE Transactions on EP - 1129 TI - Fast Image and Video Colorization Using Chrominance Blending VL - 15 SP - 1120 KW - blending KW - colorization KW - fast KW - scribbles AU - Yatziv, L AU - Sapiro, G PY - 2006/// UR - http://dx.doi.org/10.1109/TIP.2005.864231 ER -