Analyzing Spatially-varying Blur

被引：141

作者：

Chakrabarti, Ayan ^{[1
,2
]}

Zickler, Todd ^{[1
]}

Freeman, William T. ^{[2
,3
]}

机构：

[1] Harvard Univ, SEAS, Cambridge, MA 02138 USA

[2] Adobe Syst Inc, CTL, Cambridge, MA 02142 USA

[3] MIT, CSAIL, 77 Massachusetts Ave, Cambridge, MA 02139 USA

来源：

2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2010年

关键词：

MOTION ESTIMATION;

D O I：

10.1109/CVPR.2010.5539954

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Blur is caused by a pixel receiving light from multiple scene points, and in many cases, such as object motion, the induced blur varies spatially across the image plane. However, the seemingly straight-forward task of estimating spatially-varying blur from a single image has proved hard to accomplish reliably. This work considers such blur and makes two contributions: a local blur cue that measures the likelihood of a small neighborhood being blurred by a candidate blur kernel; and an algorithm that, given an image, simultaneously selects a motion blur kernel and segments the region that it affects. The methods are shown to perform well on a diversity of images.

引用

页码：2512 / 2519

页数：8