@inproceedings{3183,
  abstract     = {This paper describes two algorithms capable of real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contrast or from stereo alone is known to be error-prone. Here, colour, contrast and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, Layered Dynamic Programming (LDP), solves stereo in an extended 6-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive colour model that is learned on the fly, and stereo disparities are obtained by dynamic programming. The second algorithm, Layered Graph Cut (LGC), does not directly solve stereo. Instead the stereo match likelihood is marginalised over foreground and background hypotheses, and fused with a contrast-sensitive colour model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar perfomance, substantially better than stereo or colour/contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output.},
  author       = {Kolmogorov, Vladimir and Criminisi, Antonio and Blake, Andrew and Cross, Geoffrey and Rother, Carsten},
  booktitle    = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Volume 2 },
  isbn         = {0769523722},
  issn         = {1063-6919},
  location     = {San Diego, CA, United States},
  pages        = {407 -- 414},
  publisher    = {IEEE},
  title        = {{Bi-layer segmentation of binocular stereo video}},
  doi          = {10.1109/CVPR.2005.91},
  volume       = {2},
  year         = {2005},
}

@inproceedings{3175,
  abstract     = {This paper addresses the novel problem of automatically synthesizing an output image from a large collection of different input images. The synthesized image, called a digital tapestry, can be viewed as a visual summary or a virtual 'thumbnail' of all the images in the input collection. The problem of creating the tapestry is cast as a multi-class labeling problem such that each region in the tapestry is constructed from input image blocks that are salient and such that neighboring blocks satisfy spatial compatibility. This is formulated using a Markov Random Field and optimized via the graph cut based expansion move algorithm. The standard expansion move algorithm can only handle energies with metric terms, while our energy contains non-metric (soft and hard) constraints. Therefore we propose two novel contributions. First, we extend the expansion move algorithm for energy functions with non-metric hard constraints. Secondly, we modify it for functions with "almost" metric soft terms, and show that it gives good results in practice. The proposed framework was tested on several consumer photograph collections, and the results are presented.},
  author       = {Rother, Carsten and Kumar, Sanjiv and Kolmogorov, Vladimir and Blake, Andrew},
  booktitle    = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Volume 1},
  isbn         = {0769523722},
  issn         = {1063-6919},
  location     = {San Diego, CA, United States},
  pages        = {589 -- 596},
  publisher    = {IEEE},
  title        = {{Digital tapestry}},
  doi          = {10.1109/CVPR.2005.130},
  volume       = {1},
  year         = {2005},
}

@inproceedings{3176,
  abstract     = {This paper demonstrates the high quality, real-time segmentation techniques. We achieve real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contrast or from stereo alone is known to be error-prone. Here, colour, contrast and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, layered dynamic programming (LDP), solves stereo in an extended 6-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive colour model that is learned on the fly, and stereo disparities are obtained by dynamic programming. The second algorithm, layered graph cut (LGC), does not directly solve stereo. Instead the stereo match likelihood is marginalised over foreground and background hypotheses, and fused with a contrast-sensitive colour model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar performance, substantially better than stereo or colour/contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output.
},
  author       = {Kolmogorov, Vladimir and Criminisi, Antonio and Blake, Andrew and Cross, Geoffrey and Rother, Carsten},
  booktitle    = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  isbn         = {0769523722},
  issn         = {1063-6919},
  location     = {San Diego, CA, United States},
  pages        = {1186 -- 1186},
  publisher    = {IEEE},
  title        = {{Bi-layer segmentation of binocular stereo video}},
  doi          = {10.1109/CVPR.2005.90},
  year         = {2005},
}