Abstract
Color dimensionality reduction is believed as a non-invertible process, as re-colorization results in perceptually noticeable and unrecoverable distortion. In this article, we propose to convert a color image into a grayscale image that can fully recover its original colors, and more importantly, the encoded information is discriminative and sparse, which saves storage capacity. Particularly, we design an invertible deep neural network for color encoding and decoding purposes. This network learns to generate a residual image that encodes color information, and it is then combined with a base grayscale image for color recovering. In this way, the non-differentiable compression process (e.g., JPEG) of the base grayscale image can be integrated into the network in an end-to-end manner. To further reduce the size of the residual image, we present a specific layer to enhance Sparsity Enforcing Priors (SEP), thus leading to negligible storage space. The proposed method allows color embedding on a sparse residual image while keeping a high, 35dB PSNR on average. Extensive experiments demonstrate that the proposed method outperforms state-of-the-arts in terms of image quality and tolerability to compression.
- Mohammad Haris Baig and Lorenzo Torresani. 2017. Multiple hypothesis colorization and its application to image compression. Comput. Vis. Image Underst. 164 (2017), 111–123.Google Scholar
Cross Ref
- Johannes Ballé, Valero Laparra, and Eero P. Simoncelli. 2017. End-to-end optimized image compression. In ICLR.Google Scholar
- Zezhou Cheng, Qingxiong Yang, and Bin Sheng. 2015. Deep colorization. In ICCV. 415–423. Google Scholar
Digital Library
- Hao Du, Shengfeng He, Bin Sheng, Lizhuang Ma, and Rynson W. H. Lau. 2015. Saliency-guided color-to-gray conversion using region-based optimization. IEEE Trans. Image Proc. 24, 1 (2015), 434–443.Google Scholar
Cross Ref
- M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. 2010. The Pascal Visual Object Classes (VOC) challenge. Int. J. Comput. Vis. 88, 2 (June 2010), 303–338. Google Scholar
Digital Library
- Amy A. Gooch, Sven C. Olsen, Jack Tumblin, and Bruce Gooch. 2005. Color2gray: Salience-preserving color removal. ACM Trans Graph. 24, 3 (2005), 634–639. Google Scholar
Digital Library
- Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, and David Duvenaud. 2018. Backpropagation through the void: Optimizing control variates for black-box gradient estimation. In ICLR.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770–778.Google Scholar
- Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. In ECCV. Springer, 694–711.Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR.Google Scholar
- Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In ICLR.Google Scholar
- Gustav Larsson, Michael Maire, and Gregory Shakhnarovich. 2016. Learning representations for automatic colorization. In ECCV. 577–593.Google Scholar
- Anat Levin, Dani Lischinski, and Yair Weiss. 2004. Colorization using optimization. ACM Trans Graph., Vol. 23. 689–694. Google Scholar
Digital Library
- Mu Li, Wangmeng Zuo, Shuhang Gu, Debin Zhao, and David Zhang. 2018. Learning convolutional networks for content-weighted image compression. In CVPR. 3214–3223.Google Scholar
- Christos Louizos, Max Welling, and Diederik P. Kingma. 2018. Learning sparse neural networks through regularization. In ICLR.Google Scholar
- Cewu Lu, Li Xu, and Jiaya Jia. 2012. Real-time contrast preserving decolorization. In SIGGRAPH Asia. Google Scholar
Digital Library
- Cewu Lu, Li Xu, and Jiaya Jia. 2014. Contrast preserving decolorization with perception-based quality metrics. Int. J. Comput. Vis. 110, 2 (2014), 222–239. Google Scholar
Digital Library
- Qing Luan, Fang Wen, Daniel Cohen-Or, Lin Liang, Ying-Qing Xu, and Heung-Yeung Shum. 2007. Natural image colorization. In EGSR. 309–320. Google Scholar
Digital Library
- Yu Luo, Yong Xu, and Hui Ji. 2015. Removing rain from a single image via discriminative sparse coding. In ICCV. 3397–3405. Google Scholar
Digital Library
- Chris J. Maddison, Andriy Mnih, and Yee Whye Teh. 2016. The concrete distribution: A continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712 (2016).Google Scholar
- Ichiro Matsuda, Hirofumi Mori, and Susumu Itoh. 2000. Lossless coding of still images using minimum-rate predictors. In ICIP, Vol. 1. IEEE, 132–135.Google Scholar
Cross Ref
- Laszlo Neumann, Martin Čadík, and Antal Nemcsics. 2007. An efficient perception-based adaptive color to gray transformation. In Computational Aesthetics. 73–80. Google Scholar
Digital Library
- Yingge Qu, Tien-Tsin Wong, and Pheng-Ann Heng. 2006. Manga colorization. ACM Trans Graph., Vol. 25. 1214–1220. Google Scholar
Digital Library
- Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR.Google Scholar
- Athanassios Skodras, Charilaos Christopoulos, and Touradj Ebrahimi. 2001. The JPEG 2000 still image compression standard. IEEE Sig. Proc. Mag. 18, 5 (2001), 36–58.Google Scholar
Cross Ref
- Kaleigh Smith, Pierre-Edouard Landes, Joëlle Thollot, and Karol Myszkowski. 2008. Apparent greyscale: A simple and fast conversion to perceptually accurate images and video. Comput. Graph. Forum, Vol. 27. 193–200.Google Scholar
Cross Ref
- George Tucker, Andriy Mnih, Chris J. Maddison, John Lawson, and Jascha Sohl-Dickstein. 2017. REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models. In NeurIPS. 2627–2636. Google Scholar
Digital Library
- Gregory K. Wallace. 1992. The JPEG still picture compression standard. IEEE Trans. Consum. Electron. 38, 1 (1992), xviii–xxxiv. Google Scholar
Digital Library
- Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 3-4 (1992), 229–256. Google Scholar
Digital Library
- Menghan Xia, Xueting Liu, and Tien-Tsin Wong. 2018. Invertible grayscale. ACM Trans Graph. 37, 6 (Dec. 2018), 246:1–246:10.Google Scholar
- Li Xu, Qiong Yan, and Jiaya Jia. 2013. A sparse control model for image and video editing. ACM Trans Graph. 32, 6 (2013), 197. Google Scholar
Digital Library
- T. Ye, Y. Du, J. Deng, and S. He. 2020. Invertible grayscale via dual features ensemble. IEEE Access 8 (2020), 89670–89679.Google Scholar
Cross Ref
- Richard Zhang, Phillip Isola, and Alexei A. Efros. 2016. Colorful image colorization. In ECCV. 649–666.Google Scholar
- Richard Zhang, Jun-Yan Zhu, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, and Alexei A. Efros. 2017. Real-time user-guided image colorization with learned deep priors. ACM Trans Graph. 36, 4 (2017), 119:1–119:11. Google Scholar
Digital Library
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networkss. In ICCV.Google Scholar
Index Terms
Invertible Grayscale with Sparsity Enforcing Priors
Recommendations
Invertible grayscale
Once a color image is converted to grayscale, it is a common belief that the original color cannot be fully restored, even with the state-of-the-art colorization methods. In this paper, we propose an innovative method to synthesize invertible grayscale. ...
Using assorted color spaces and pixel window sizes for colorization of grayscale images
ICWET '10: Proceedings of the International Conference and Workshop on Emerging Trends in TechnologyThere is no exact solution for colorization of grayscale images. In the initial work done [23], color traits transfer techniques to color grayscale images are proposed. The main focus of the techniques [23] is to minimise the human efforts needed in ...
A Novel Approach for Colorization of a Grayscale Image using Soft Computing Techniques
Colorization of grayscale image is a process to convert a grayscale image into a color one. Few research works reported in literature on this but there is hardly any generalized method that successfully colorizes all types of grayscale image. This study ...






Comments