Bolun Cai Xiangmin Xu Xiaofen Xing
South China University of Technology
 |
Perception preserving decolorization. We use a loss network (VGG-19) pretrained for object categorization to define multi-level perceptual loss functions, which measure perceptual differences between the grayscale and color images. The loss network remains fixed during the optimization process. |
Abstract
Decolorization is a basic tool to transform a color image into a grayscale image, which is used in digital printing, stylized black-and-white photography, and in many single-channel image processing applications. While recent researches focus on retaining as much as possible meaningful visual features and color contrast. In this paper, we explore how to use deep neural networks for decolorization, and propose an optimization approach aiming at perception preserving. The system uses deep representations to extract content information based on human visual perception, and automatically selects suitable grayscale for decolorization. The evaluation experiments show the effectiveness of the proposed method.
Color-to-gray Conversion
 |
 |
| (a) Input | (b) Ours |
 |
 |
 |
 |
 |
 |
| (c) L of CIELab | (d) Matalab | (e) Color2Gray | (f) Bala04 | (g) Rasche05 | (h) Lu12 |
Results
| Color Input | State-of-the-art | Ours |
Downloads
 |
"Perception Preserving Decolorization" Bolun Cai, Xiangmin Xu, Xiaofen Xing submitted to IEEE International Conference on Image Processing (ICIP), 2018  [Paper (10.6M)] [Poster (12.6MB)] [Code] |
Last update: Tue 20, 2018
