? 基于细节字典学习的照片表面增强
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) :417-429    DOI: 10.1007/s11390-017-1733-z
Special Issue on Software Engineering for High-Confidence Systems << Previous Articles | Next Articles >>
基于细节字典学习的照片表面增强
Zhi-Feng Xie1,2, Shi Tang1, Dong-Jin Huang1,2, You-Dong Ding1,2, Member, CCF, Li-Zhuang Ma2,3, Member, CCF
1. Department of Film and Television Engineering, Shanghai University, Shanghai 200072, China;
2. Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China;
3. Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Photographic Appearance Enhancement via Detail-based Dictionary Learning
Zhi-Feng Xie1,2, Shi Tang1, Dong-Jin Huang1,2, You-Dong Ding1,2, Member, CCF, Li-Zhuang Ma2,3, Member, CCF
1. Department of Film and Television Engineering, Shanghai University, Shanghai 200072, China;
2. Shanghai Engineering Research Center of Motion Picture Special Effects, Shanghai 200072, China;
3. Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

摘要
参考文献
相关文章
Download: [PDF 6292KB]  
摘要 许多边缘感知的滤波器通过细节分解和增强,能够高效地增强图像的表面。但是,由于一些可视化的表面缺陷,尤其是噪声、晕、不自然的对比度等,这些方法经常不能生成照片级表面的增强效果。关键的原因在于增强过程中对高质量表面的引导与约束不够充分。因此,本文期望从大量高质量图像小块中训练一个细节字典,进一步约束和控制整个表面增强。在这篇论文中,我们提出一种基于学习的照片级表面增强方法,包括两个主要步骤:字典训练和稀疏重建。在训练阶段,我们从很多高质量的照片中抽取大量的细节小块组成训练集,然后通过迭代地优化一个L1-norm能量方程,训练一个过完备的细节字典。在重建阶段,我们利用训练的字典重建增强的细节层,并且形式化一个梯度引导的优化方程来提升小块间的局部连贯性。此外,我们提出了两种评价方式来评测表面增强方法的效果。最终的实验结果验证了我们基于学习的增强方法的有效性。
关键词图像增强   字典学习   边缘感知的滤波     
Abstract: A number of edge-aware filters can efficiently boost the appearance of an image by detail decomposition and enhancement. However, they often fail to produce photographic enhanced appearance due to some visible artifacts, especially noise, halos and unnatural contrast. The essential reason is that the guidance and constraint of high-quality appearance aren't enough sufficient in the process of enhancement. Thus our idea is to train a detail dictionary from a lot of high-quality patches in order to constrain and control the entire appearance enhancement. In this paper, we propose a novel learning-based enhancement method for photographic appearance, which includes two main stages: dictionary training and sparse reconstruction. In the training stage, we construct a training set of detail patches by extracting from some high-quality photos, and then train an overcomplete detail dictionary by iteratively minimizing an L1-norm energy function. In the reconstruction stage, we employ the trained dictionary to reconstruct the boosted detail layer, and further formalize a gradient-guided optimization function to improve the local coherence between patches. Moreover, we propose two evaluation metrics to measure the performance of appearance enhancement. The final experimental results have demonstrated the effectiveness of our learning-based enhancement method.
Keywordsimage enhancement   dictionary learning   edge-aware filter     
Received 2016-12-09;
本文基金:

This work was supported by the National Natural Science Foundation of China under Grant Nos.61303093,61402278,and 61472245,the Innovation Program of the Science and Technology Commission of Shanghai Municipality of China under Grant No.16511101300,the Natural Science Foundation of Shanghai under Grant No.14ZR1415800,and the Gaofeng Film Discipline Grant of Shanghai Municipal Education Commission.

About author: Zhi-Feng Xie received his Ph.D. degree in computer application technology from Shanghai Jiao Tong University, Shanghai, in 2013. He was a research assistant at the Department of Computer Science, City University of Hong Kong, Hong Kong, in 2011. He is now an assistant professor with Shanghai University, Shanghai. His research interests include image/video editing, computer graphics, and digital media technology.
引用本文:   
Zhi-Feng Xie, Shi Tang, Dong-Jin Huang, You-Dong Ding, Li-Zhuang Ma.基于细节字典学习的照片表面增强[J]  Journal of Computer Science and Technology , 2017,V32(3): 417-429
Zhi-Feng Xie, Shi Tang, Dong-Jin Huang, You-Dong Ding, Li-Zhuang Ma.Photographic Appearance Enhancement via Detail-based Dictionary Learning[J]  Journal of Computer Science and Technology, 2017,V32(3): 417-429
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1733-z
Copyright 2010 by Journal of Computer Science and Technology