Interactive Removal of Shadows from a Single Image Using Hierarchical Graph Cut

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.

[1]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[2]  Jérôme Darbon,et al.  Image Restoration with Discrete Constrained Total Variation Part I: Fast and Exact Optimization , 2006, Journal of Mathematical Imaging and Vision.

[3]  Y. Weiss,et al.  Separating reflections from a single image using local features , 2004, CVPR 2004.

[4]  Andrew Blake,et al.  LogCut - Efficient Graph Cut Optimization for Markov Random Fields , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[5]  Takeo Kanade,et al.  Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing , 2007, ACCV.

[6]  Jian Sun,et al.  Lazy snapping , 2004, SIGGRAPH 2004.

[7]  Claus B. Madsen,et al.  Graph Cut Based Segmentation of Soft Shadows for Seamless Removal and Augmentation , 2007, SCIA.

[8]  Yair Weiss,et al.  Deriving intrinsic images from image sequences , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[9]  Zhi-Qiang Liu,et al.  Self-Validated and Spatially Coherent Clustering with Net-Structured MRF and Graph Cuts , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[10]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Tai-Pang Wu,et al.  A Bayesian approach for shadow extraction from a single image , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[12]  Nikos Komodakis,et al.  Fast, Approximately Optimal Solutions for Single and Dynamic MRFs , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[14]  Hiroshi Ishikawa,et al.  Exact Optimization for Markov Random Fields with Convex Priors , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Daniel Cremers,et al.  A Convex Formulation of Continuous Multi-label Problems , 2008, ECCV.

[16]  Daniel P. Huttenlocher,et al.  Learning for stereo vision using the structured support vector machine , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Katsushi Ikeuchi,et al.  Median Photometric Stereo as Applied to the Segonko Tumulus and Museum Objects , 2009, International Journal of Computer Vision.

[18]  Masashi Baba,et al.  Shadow removal from a real image based on shadow density , 2004, SIGGRAPH '04.

[19]  Leo Grady,et al.  A multilevel banded graph cuts method for fast image segmentation , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[20]  Edward H. Adelson,et al.  Recovering intrinsic images from a single image , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[22]  Katsushi Ikeuchi,et al.  Illumination normalization with time-dependent intrinsic images for video surveillance , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Harry Shum,et al.  Natural shadow matting , 2007, TOGS.

[24]  Graham D. Finlayson,et al.  Simple Shadow Remova , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[25]  Christopher Joseph Pal,et al.  Learning Conditional Random Fields for Stereo , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Giuseppe Scarpa,et al.  A tree-structured Markov random field model for Bayesian image segmentation , 2003, IEEE Trans. Image Process..

[27]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Hagit Hel-Or,et al.  Texture-Preserving Shadow Removal in Color Images Containing Curved Surfaces , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Cheng Lu,et al.  Intrinsic Images by Entropy Minimization , 2004, ECCV.

[30]  Olivier Juan,et al.  Active Graph Cuts , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).