| 1. |
- Boykov, Yuri, et al.
(författare)
-
Guest Editorial: Energy Optimization Methods
- 2013
-
Ingår i: International Journal of Computer Vision. - : Springer Science and Business Media LLC. - 1573-1405 .- 0920-5691. ; 104:3, s. 221-222
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 2. |
- Boykov, Yuri, et al.
(författare)
-
Volumetric bias in segmentation and reconstruction : Secrets and solutions
- 2016
-
Ingår i: Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. - 9781467383912 ; 11-18-December-2015, s. 1769-1777
-
Konferensbidrag (refereegranskat)abstract
- Many standard optimization methods for segmentation and reconstruction compute ML model estimates for ap- pearance or geometry of segments, e.g. Zhu-Yuille [23], Torr [20], Chan-Vese [6], GrabCut [18], Delong et al. [8]. We observe that the standard likelihood term in these formu- lations corresponds to a generalized probabilistic K-means energy. In learning it is well known that this energy has a strong bias to clusters of equal size [11], which we express as a penalty for KL divergence from a uniform distribution of cardinalities. However, this volumetric bias has been mostly ignored in computer vision. We demonstrate signif- icant artifacts in standard segmentation and reconstruction methods due to this bias. Moreover, we propose binary and multi-label optimization techniques that either (a) remove this bias or (b) replace it by a KL divergence term for any given target volume distribution. Our general ideas apply to continuous or discrete energy formulations in segmenta- tion, stereo, and other reconstruction problems.
|
|
| 3. |
- Olsson, Carl, et al.
(författare)
-
Curvature-Based Regularization for Surface Approximation
- 2012
-
Ingår i: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). - 1063-6919. ; , s. 1576-1583
-
Konferensbidrag (refereegranskat)abstract
- We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noisy) data point by minimizing the squared distances to the points and the irregularity of the surface implicitly defined by the tangent planes. In order to avoid the well-known "shrinking" bias associated with first-order surface regularization, we choose a robust smoothing term that approximates curvature of the underlying surface. In contrast to a number of recent publications estimating curvature using discrete (e. g. binary) labellings with triple-cliques we use higher-dimensional labels that allows modeling curvature with only pair-wise interactions. Hence, many standard optimization algorithms (e. g. message passing, graph cut, etc) can minimize the proposed curvature-based regularization functional. The accuracy of our approach for representing curvature is demonstrated by theoretical and empirical results on synthetic and real data sets from multi-view reconstruction and stereo. (1)
|
|
| 4. |
- Olsson, Carl, et al.
(författare)
-
In Defense of 3D-Label Stereo
- 2013
-
Ingår i: Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. - 1063-6919 .- 2163-6648. ; , s. 1730-1737
-
Konferensbidrag (refereegranskat)abstract
- It is commonly believed that higher order smoothness should be modeled using higher order interactions. For example, 2nd order derivatives for deformable (active) contours are represented by triple cliques. Similarly, the 2nd order regularization methods in stereo predominantly use MRF models with scalar (1D) disparity labels and triple clique interactions. In this paper we advocate a largely overlooked alternative approach to stereo where 2nd order surface smoothness is represented by pairwise interactions with 3D-labels, e.g. tangent planes. This general paradigm has been criticized due to perceived computational complexity of optimization in higher-dimensional label space. Contrary to popular beliefs, we demonstrate that representing 2nd order surface smoothness with 3D labels leads to simpler optimization problems with (nearly) submodular pairwise interactions. Our theoretical and experimental results demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo.
|
|
| 5. |
- Olsson, Carl, et al.
(författare)
-
Partial Enumeration and Curvature Regularization
- 2013
-
Ingår i: Computer Vision (ICCV), 2013 IEEE International Conference on. - 1550-5499. ; , s. 2936-2943
-
Konferensbidrag (refereegranskat)abstract
- Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power. Optimization of such energies, however, is generally NP-hard. A naive approach that works for small problem instances is exhaustive search, that is, enumera- tion of all possible labelings of the underlying graph. We propose a general minimization approach for large graphs based on enumeration of labelings of certain small patches. This partial enumeration technique reduces complex high- order energy formulations to pairwise Constraint Satisfac- tion Problems with unary costs (uCSP), which can be ef- ficiently solved using standard methods like TRW-S. Our approach outperforms a number of existing state-of-the-art algorithms on well known difficult problems (e.g. curvature regularization, stereo, deconvolution); it gives near global minimum and better speed. Our main application of interest is curvature regular- ization. In the context of segmentation, our partial enu- meration technique allows to evaluate curvature directly on small patches using a novel integral geometry approach.
|
|
