? 提升空间一致性与边缘定位的图像自动上色方法
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (3) :494-506    DOI: 10.1007/s11390-017-1739-6
Special Issue on Software Engineering for High-Confidence Systems << Previous Articles | Next Articles >>
提升空间一致性与边缘定位的图像自动上色方法
Wei Zhang1, Member, IEEE, Chao-Wei Fang1, Guan-Bin Li2,*, Member, IEEE
1. Department of Computer Science, The University of Hong Kong, Hong Kong, China;
2. School of Data and Computer Science, Sun Yat-sen University, Guangzhou 510006, China
Automatic Colorization with Improved Spatial Coherence and Boundary Localization
Wei Zhang1, Member, IEEE, Chao-Wei Fang1, Guan-Bin Li2,*, Member, IEEE
1. Department of Computer Science, The University of Hong Kong, Hong Kong, China;
2. School of Data and Computer Science, Sun Yat-sen University, Guangzhou 510006, China

摘要
参考文献
相关文章
Download: [PDF 4063KB]  
摘要 给灰度图像上色是计算机图形学中的一个重要的问题并且存在很多的应用。最近的研究将图像全自动上色看作一个对图像中每个像素颜色值进行预测的问题,同时利用了深度卷积神经网络,使得图像全自动上色技术取得了显著的进步。然而,当前的结果距离高质量的全自动上色依旧存在很大的距离。具体来说,在目前的算法结果中,普遍存在两类问题,一是色彩平滑的区域内部常常无法得到较为一致的上色结果,二是在图像内部不同区域的边界处,会出现颜色溢出。为了解决这些问题,我们提出了新的全自动图像上色的算法流程,其中包含了一个边界指导的条件随机场以及基于卷积神经网络的颜色变换作为后处理步骤。此外,因为每张图片往往存在多种合理的上色方案,对算法上色结果的优劣进行自动评价也是一项有挑战性的工作。我们进一步提出两个全新的自动评价体系,使得可以从区域内上色的一致性和边界保持这两个方面对上色结果进行有效的评价。实验结果表明,在多种评价体系下,我们提出的算法能够得到更好的自动上色结果。
关键词自动上色   深度学习   条件随机场   颜色变换   质量评价     
Abstract: Grayscale image colorization is an important computer graphics problem with a variety of applications. Recent fully automatic colorization methods have made impressive progress by formulating image colorization as a pixel-wise prediction task and utilizing deep convolutional neural networks. Though tremendous improvements have been made, the result of automatic colorization is still far from perfect. Specifically, there still exist common pitfalls in maintaining color consistency in homogeneous regions as well as precisely distinguishing colors near region boundaries. To tackle these problems, we propose a novel fully automatic colorization pipeline which involves a boundary-guided CRF (conditional random field) and a CNN-based color transform as post-processing steps. In addition, as there usually exist multiple plausible colorization proposals for a single image, automatic evaluation for different colorization methods remains a challenging task. We further introduce two novel automatic evaluation schemes to efficiently assess colorization quality in terms of spatial coherence and localization. Comprehensive experiments demonstrate great quality improvement in results of our proposed colorization method under multiple evaluation metrics.
Keywordsautomatic colorization   deep learning   conditional random field(CRF)   color transform   quality evaluation     
Received 2016-12-25;
本文基金:

This work was partially supported by Hong Kong Research Grants Council under General Research Funds (HKU17209714).

通讯作者: Guan-Bin Li     Email: liguanbin@mail.sysu.edu.cn
About author: Wei Zhang is a Ph.D. candidate at the Department of Computer Science, The University of Hong Kong, Hong Kong. He received his B.E. degree in automation from Chongqing University, Chongqing, in 2010, and M.S. degree in pattern recognition and artificial intelligence from Huazhong University of Science and Technology, Wuhan, in 2013. His research interest covers image colorization and boundary detection.
引用本文:   
Wei Zhang, Chao-Wei Fang, Guan-Bin Li.提升空间一致性与边缘定位的图像自动上色方法[J]  Journal of Computer Science and Technology , 2017,V32(3): 494-506
Wei Zhang, Chao-Wei Fang, Guan-Bin Li.Automatic Colorization with Improved Spatial Coherence and Boundary Localization[J]  Journal of Computer Science and Technology, 2017,V32(3): 494-506
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1739-6
Copyright 2010 by Journal of Computer Science and Technology