期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 30, 期 -, 页码 6081-6095出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2021.3091902
关键词
Gray-scale; Image color analysis; Color; Image restoration; Neural networks; Image reconstruction; Image coding; Invertible learning; image decolorization; color restoration; invertible neural networks; wavelet decomposition
资金
- Hong Kong Research Grants Council (RGC) Research Impact Fund (RIF) [R5001-18]
The proposed method utilizes invertible neural networks to generate invertible grayscale images by encoding color information into Gaussian distributed latent variables, ensuring that the lost color information in grayscale generation is independent of the input color image. Experimental results demonstrate that the method achieves state-of-the-art performance in both qualitative and quantitative aspects.
Invertible image decolorization is a useful color compression technique to reduce the cost in multimedia systems. Invertible decolorization aims to synthesize faithful grayscales from color images, which can be fully restored to the original color version. In this paper, we propose a novel color compression method to produce invertible grayscale images using invertible neural networks (INNs). Our key idea is to separate the color information from color images, and encode the color information into a set of Gaussian distributed latent variables via INNs. By this means, we force the color information lost in grayscale generation to be independent of the input color image. Therefore, the original color version can be efficiently recovered by randomly re-sampling a new set of Gaussian distributed variables, together with the synthetic grayscale, through the reverse mapping of INNs. To effectively learn the invertible grayscale, we introduce the wavelet transformation into a UNet-like INN architecture, and further present a quantization embedding to prevent the information omission in format conversion, which improves the generalizability of the framework in real-world scenarios. Extensive experiments on three widely used benchmarks demonstrate that the proposed method achieves a state-of-the-art performance in terms of both qualitative and quantitative results, which shows its superiority in multimedia communication and storage systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据