Paper Info
Title
Single-image shadow detection and removal using paired regions
Abstract
In this paper, we address the problem of shadow detection and removal from single images of natural scenes. Different from traditional methods that explore pixel or edge information, we employ a region based approach. In addition to considering individual regions separately, we predict relative illumination conditions between segmented regions from their appearances and perform pairwise classification based on such information. Classification results are used to build a graph of segments, and graph-cut is used to solve the labeling of shadow and non-shadow regions. Detection results are later refined by image matting, and the shadow free image is recovered by relighting each pixel based on our lighting model. We evaluate our method on the shadow detection dataset. In addition, we created a new dataset with shadow-free ground truth images, which provides a quantitative basis for evaluating shadow removal.
Year
DOI
Venue
2011
10.1109/CVPR.2011.5995725
CVPR
Keywords
Field
DocType
hidden feature removal,single-image shadow detection,pairwise classification,shadow free image,classification result,image segmentation,region segmentation,image recognition,new dataset,natural scene,image recovery,single image shadow detection,image matting,shadow detection,image classification,graph cut,shadow free ground truth image,shadow removal,shadow detection dataset,edge information,natural scenes,single images removal,graph theory,detection result,robustness,materials,histograms,lighting,ground truth
Graph theory,Cut,Shadow,Computer vision,Pairwise comparison,Pattern recognition,Computer science,Image segmentation,Ground truth,Pixel,Artificial intelligence,Contextual image classification
Conference
Volume
Issue
ISSN
2011
1
1063-6919
ISBN
Citations 
PageRank 
978-1-4577-0394-2
75
2.29
References 
Authors
15
3
Name
Order
Citations
PageRank
Ruiqi Guo156422.10
Qieyun Dai221719.85
Derek Hoiem34998302.66