UniHIST: A Unified Framework for Image Restoration With Marginal Histogram Constraints

	UniHIST: A Unified Framework for Image Restoration With Marginal Histogram Constraints
	Mei, Xing1,2 ; Dong, Weiming2 ; Hu, Bao-Gang2 ; Lyu, Siwei 1
	2015-06
会议名称	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议录名称	IEEE Conference on Computer Vision and Pattern Recognition
会议日期	2015-6
会议地点	Boston, MA
摘要	Marginal histograms provide valuable information for various computer vision problems. However, current image restoration methods do not fully exploit the potential of marginal histograms, in particular, their role as ensemble constraints on the marginal statistics of the restored image. In this paper, we introduce a new framework, Uni-HIST, to incorporate marginal histogram constraints into image restoration. The key idea of UniHIST is to minimize the discrepancy between the marginal histograms of the restored image and the reference histograms in pixel or gradient domains using the quadraticWasserstein (W2) distance. TheW2 distance can be computed directly from data without resorting to density estimation. It provides a differentiable metric between marginal histograms and allows easy integration with existing image restoration methods. We demonstrate the effectiveness of UniHIST through denoising of pattern images and non-blind deconvolution of natural images. We show that UniHIST enhances restoration performance and leads to visual and quantitative improvements over existing state-of-the-art methods.
关键词	Image Restoration
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11193
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Mei, Xing
作者单位	1.Computer Science Department, University at Albany, SUNY 2.Institute of Automation, Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Mei, Xing,Dong, Weiming,Hu, Bao-Gang,et al. UniHIST: A Unified Framework for Image Restoration With Marginal Histogram Constraints[C],2015.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
UniHIST_A unified fr（2059KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载