@inproceedings{3184,
abstract = {Algorithms for discrete energy minimization play a fundamental role for low-level vision. Known techniques include graph cuts, belief propagation (BP) and recently introduced tree-reweighted message passing (TRW). So far, the standard benchmark for their comparison has been a 4-connected grid-graph arising in pixel-labelling stereo. This minimization problem, however, has been largely solved: recent work shows that for many scenes TRW finds the global optimum. Furthermore, it is known that a 4-connecled grid-graph is a poor stereo model since it does not take occlusions into account. We propose the problem of stereo with occlusions as a new test bed for minimization algorithms. This is a more challenging graph since it has much larger connectivity, and it also serves as a better stereo model. An attractive feature of this problem is that increased connectivity does not result in increased complexity of message passing algorithms. Indeed, one contribution of this paper is to show that sophisticated implementations of BP and TRW have the same time and memory complexity as that of 4-connecled grid-graph stereo. The main conclusion of our experimental study is that for our problem graph cut outperforms both TRW and BP considerably. TRW achieves consistently a lower energy than BP. However, as connectivity increases the speed of convergence of TRW becomes slower. Unlike 4-connected grids, the difference between the energy of the best optimization method and the lower bound of TRW appears significant. This shows the hardness of the problem and motivates future research.},
author = {Vladimir Kolmogorov and Rother, Carsten},
pages = {1 -- 15},
publisher = {Springer},
title = {{Comparison of energy minimization algorithms for highly connected graphs}},
doi = {10.1007/11744047_1},
volume = {3952 LNCS},
year = {2006},
}
@article{3185,
abstract = {This paper describes models and algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from color/contrast or from stereo alone is known to be error-prone. Here, color, 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 six-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive color 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 marginalized over disparities to evaluate foreground and background hypotheses and then fused with a contrast-sensitive color 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 either stereo or color/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 = {Vladimir Kolmogorov and Criminisi, Antonio and Blake, Andrew and Cross, Geoffrey and Rother, Carsten},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
number = {9},
pages = {1480 -- 1492},
publisher = {IEEE},
title = {{Probabilistic fusion of stereo with color and contrast for bilayer segmentation}},
doi = {10.1109/TPAMI.2006.193},
volume = {28},
year = {2006},
}
@inproceedings{3186,
abstract = {We introduce a new approach to modelling gradient flows of contours and surfaces. While standard variational methods (e.g. level sets) compute local interface motion in a differential fashion by estimating local contour velocity via energy derivatives, we propose to solve surface evolution PDEs by explicitly estimating integral motion of the whole surface. We formulate an optimization problem directly based on an integral characterization of gradient flow as an infinitesimal move of the (whole) surface giving the largest energy decrease among all moves of equal size. We show that this problem can be efficiently solved using recent advances in algorithms for global hypersurface optimization [4, 2, 11]. In particular, we employ the geo-cuts method [4] that uses ideas from integral geometry to represent continuous surfaces as cuts on discrete graphs. The resulting interface evolution algorithm is validated on some 2D and 3D examples similar to typical demonstrations of level-set methods. Our method can compute gradient flows of hypersurfaces with respect to a fairly general class of continuous functional and it is flexible with respect to distance metrics on the space of contours/surfaces. Preliminary tests for standard L2 distance metric demonstrate numerical stability, topological changes and an absence of any oscillatory motion.},
author = {Boykov, Yuri and Vladimir Kolmogorov and Cremers, Daniel and Delong, Andrew},
pages = {409 -- 422},
publisher = {Springer},
title = {{An integral solution to surface evolution PDEs via geo cuts}},
doi = {10.1007/11744078_32},
volume = {3953},
year = {2006},
}
@inproceedings{3188,
abstract = {We introduce the term cosegmentation which denotes the task of segmenting simultaneously the common parts of an image pair. A generative model for cosegmentation is presented. Inference in the model leads to minimizing an energy with an MRF term encoding spatial coherency and a global constraint which attempts to match the appearance histograms of the common parts. This energy has not been proposed previously and its optimization is challenging and NP-hard. For this problem a novel optimization scheme which we call trust region graph cuts is presented. We demonstrate that this framework has the potential to improve a wide range of research: Object driven image retrieval, video tracking and segmentation, and interactive image editing. The power of the framework lies in its generality, the common part can be a rigid/non-rigid object (or scene), observed from different viewpoints or even similar objects of the same class.},
author = {Rother, Carsten and Vladimir Kolmogorov and Minka, Thomas P and Blake, Andrew},
pages = {993 -- 1000},
publisher = {IEEE},
title = {{Cosegmentation of image pairs by histogram matching - Incorporating a global constraint into MRFs}},
doi = {10.1109/CVPR.2006.91},
year = {2006},
}
@inproceedings{3189,
abstract = {This paper presents an algorithm capable of real-time separation of foreground from background in monocular video sequences. Automatic segmentation of layers from colour/contrast or from motion alone is known to be error-prone. Here motion, colour and contrast cues are probabilistically fused together with spatial and temporal priors to infer layers accurately and efficiently. Central to our algorithm is the fact that pixel velocities are not needed, thus removing the need for optical flow estimation, with its tendency to error and computational expense. Instead, an efficient motion vs non-motion classifier is trained to operate directly and jointly on intensity-change and contrast. Its output is then fused with colour information. The prior on segmentation is represented by a second order, temporal, Hidden Markov Model, together with a spatial MRF favouring coherence except where contrast is high. Finally, accurate layer segmentation and explicit occlusion detection are efficiently achieved by binary graph cut. The segmentation accuracy of the proposed algorithm is quantitatively evaluated with respect to existing ground-truth data and found to be comparable to the accuracy of a state of the art stereo segmentation algorithm. Fore-ground/background segmentation is demonstrated in the application of live background substitution and shown to generate convincingly good quality composite video.},
author = {Criminisi, Antonio and Cross, Geoffrey and Blake, Andrew and Vladimir Kolmogorov},
pages = {53 -- 60},
publisher = {IEEE},
title = {{Bilayer segmentation of live video}},
doi = {10.1109/CVPR.2006.69},
volume = {1},
year = {2006},
}