Interactive shadow removal from a single image using hierarchical graph cut

Authors:
Daisuke Miyazaki;Yasuyuki Matsushita;Katsushi Ikeuchi
Affiliations:
Institute of Industrial Science, The University of Tokyo, Tokyo, Japan;Microsoft Research Asia, Sigma Center, Beijing, P.R.C.;Institute of Industrial Science, The University of Tokyo, Tokyo, Japan
Venue:
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Year:
2009

Citing 17
Cited 6

Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lazy snapping

ACM SIGGRAPH 2004 Papers
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
Illumination Normalization with Time-Dependent Intrinsic Images for Video Surveillance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recovering Intrinsic Images from a Single Image

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multilevel Banded Graph Cuts Method for Fast Image Segmentation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
A Bayesian Approach for Shadow Extraction from a Single Image

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Active Graph Cuts

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Simple Shadow Remova

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Self-Validated and Spatially Coherent Clustering with Net-Structured MRF and Graph Cuts

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Shadow removal from a real image based on shadow density

SIGGRAPH '04 ACM SIGGRAPH 2004 Posters
Image Restoration with Discrete Constrained Total Variation Part I: Fast and Exact Optimization

Journal of Mathematical Imaging and Vision
Natural shadow matting

ACM Transactions on Graphics (TOG)
Graph cut based segmentation of soft shadows for seamless removal and augmentation

SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Image segmentation using iterated graph cuts based on multi-scale smoothing

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Exact optimization for Markov random fields with convex priors

IEEE Transactions on Pattern Analysis and Machine Intelligence
A tree-structured Markov random field model for Bayesian image segmentation

IEEE Transactions on Image Processing

3D objects localization using fuzzy approach and hierarchical belief propagation: application at level crossings

Journal on Image and Video Processing - Special issue on advanced video-based surveillance
Review article: A 1D approach to correlation-based stereo matching

Image and Vision Computing
Removing shadows for color projection using sun position estimation

VAST'10 Proceedings of the 11th International conference on Virtual Reality, Archaeology and Cultural Heritage
SCoBeP: Dense image registration using sparse coding and belief propagation

Journal of Visual Communication and Image Representation
Special section on CAD/Graphics 2013: Image-based relighting from a sparse set of outdoor images

Computers and Graphics
A homography transform based higher-order MRF model for stereo matching

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a method for extracting a shadow matte from a single image. The removal of shadows from a single image is a difficult problem to solve unless additional information is available. We use user-supplied hints to solve the problem. The proposed method estimates a fractional shadow matte using a graph cut energy minimization approach. We present a new hierarchical graph cut algorithm that efficiently solves the multi-labeling problems, allowing our approach to run at interactive speeds. The effectiveness of the proposed shadow removal method is demonstrated using various natural images, including aerial photographs.