QQ客服 官方微博 反馈留言

	Recovering Intrinsic Images From Image Sequences Using Total Variation Models
	Xiaohua Xie; Wenyong Gong; Minglun Gong; Tieru Wu
	2015
会议名称	2015 IEEE International Conference on Image Processing
会议地点	Quebec City/Canada
英文摘要	Recovering intrinsic images from natural photos is one of the foundational problems in computer vision. This mission always falls into an ill-posed problem. In order to attain reasonable estimations, one strategy is to use multiple images of the scene under various lightings so as to narrow the solution space, whereas another is to utilize priori knowledge as constraints. In this paper, we present an approach to deriving intrinsic images (including illumination images and reflectance images) that employs both strategies. Specifically, the Total Variation (TV) constraint is imposed because of its excellent edge preservation ability and simple parameter settings. To solve this objective function efficiently, we propose using the Alternating Direction Method of Multipliers (ADMM) to build an iterative numerical scheme. Experimental results illustrate the effectiveness of the proposed model and the numerical scheme.
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/6965]
专题	深圳先进技术研究院_数字所
作者单位	2015
推荐引用方式 GB/T 7714	Xiaohua Xie,Wenyong Gong,Minglun Gong,et al. Recovering Intrinsic Images From Image Sequences Using Total Variation Models[C]. 见:2015 IEEE International Conference on Image Processing. Quebec City/Canada.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。