Results 1  10
of
46
Applications of parametric maxflow in computer vision
"... The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linearly on parameter λ. In this paper we study vision applications for which it is important to solve the maxflow problem for ..."
Abstract

Cited by 59 (9 self)
 Add to MetaCart
(Show Context)
The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linearly on parameter λ. In this paper we study vision applications for which it is important to solve the maxflow problem for different λ’s. An example is a weighting between data and regularization terms in image segmentation or stereo: it is desirable to vary it both during training (to learn λ from ground truth data) and testing (to select best λ using highknowledge constraints, e.g. user input). We review algorithmic aspects of this parametric maximum flow problem previously unknown in vision, such as the ability to compute all breakpoints of λ and corresponding optimal configurations in finite time. These results allow, in particular, to minimize the ratio of some geometric functionals, such as flux of a vector field over length (or area). Previously, such functionals were tackled with shortest path techniques applicable only in 2D. We give theoretical improvements for “PDE cuts ” [5]. We present experimental results for image segmentation, 3D reconstruction, and the cosegmentation problem. 1.
A scalable graphcut algorithm for nd grids
 In Proceedings of CVPR
, 2008
"... Global optimisation via st graph cuts is widely used in computer vision and graphics. To obtain highresolution output, graph cut methods must construct massive ND gridgraphs containing billions of vertices. We show that when these graphs do not fit into physical memory, current maxflow/mincut ..."
Abstract

Cited by 41 (0 self)
 Add to MetaCart
(Show Context)
Global optimisation via st graph cuts is widely used in computer vision and graphics. To obtain highresolution output, graph cut methods must construct massive ND gridgraphs containing billions of vertices. We show that when these graphs do not fit into physical memory, current maxflow/mincut algorithms—the workhorse of graph cut methods—are totally impractical. Others have resorted to banded or hierarchical approximation methods that get trapped in local minima, which loses the main benefit of global optimisation. We enhance the pushrelabel algorithm for maximum flow [14] with two practical contributions. First, true global minima can now be computed on immense gridlike graphs too large for physical memory. These graphs are ubiquitous in computer vision, medical imaging and graphics. Second, for commodity multicore platforms our algorithm attains nearlinear speedup with respect to number of processors. To achieve these goals, we generalised the standard relabeling operations associated with pushrelabel. 1.
Registration of 3D Point Clouds and Meshes: A Survey From Rigid to NonRigid
"... Abstract—3D surface registration transforms multiple 3D datasets into the same coordinate system so as to align overlapping components of these sets. Recent surveys have covered different aspects of either rigid or nonrigid registration, but seldom discuss them as a whole. Our study serves two purp ..."
Abstract

Cited by 33 (4 self)
 Add to MetaCart
(Show Context)
Abstract—3D surface registration transforms multiple 3D datasets into the same coordinate system so as to align overlapping components of these sets. Recent surveys have covered different aspects of either rigid or nonrigid registration, but seldom discuss them as a whole. Our study serves two purposes: (i) to give a comprehensive survey of both types of registration, focusing on 3D point clouds and meshes, and (ii) to provide a better understanding of registration from the perspective of data fitting. Registration is closely related to data fitting in that it comprises three core interwoven components: model selection, correspondences & constraints and optimization. Study of these components (i) provides a basis for comparison of the novelties of different techniques, (ii) reveals the similarity of rigid and nonrigid registration in terms of problem representations, and (iii) shows how overfitting arises in nonrigid registration and the reasons for increasing interest in intrinsic techniques. We further summarise some practical issues of registration which include initializations and evaluations, and discuss some of our own observations, insights and foreseeable research trends. Index Terms—Deformation modeling, digital geometry processing, surface registration, point clouds, meshes, 3D scanning 1
Completion and Reconstruction with Primitive Shapes
 Computer Graphics Forum (Proc. of Eurographics
, 2009
"... Figure 1: Reconstruction of the fandisk model. Orange color signifies completed surface parts. (a) The input pointcloud with holes (b) Final result (c) Result without the connectivity enforcement algorithm of Sec. 5. The disconnected primitive highlighted in red cuts off part of the model. (d) Clos ..."
Abstract

Cited by 26 (0 self)
 Add to MetaCart
(Show Context)
Figure 1: Reconstruction of the fandisk model. Orange color signifies completed surface parts. (a) The input pointcloud with holes (b) Final result (c) Result without the connectivity enforcement algorithm of Sec. 5. The disconnected primitive highlighted in red cuts off part of the model. (d) Closeup views of result without consistent edge labels and final result (see Sec. 7) We consider the problem of reconstruction from incomplete pointclouds. To find a closed mesh the reconstruction is guided by a set of primitive shapes which has been detected on the input pointcloud (e.g. planes, cylinders etc.). With this guidance we not only continue the surrounding structure into the holes but also synthesize plausible edges and corners from the primitives ’ intersections. To this end we give a surface energy functional that incorporates the primitive shapes in a guiding vector field. The discretized functional can be minimized with an efficient graphcut algorithm. A novel greedy optimization strategy is proposed to minimize the functional under the constraint that surface parts corresponding to a given primitive must be connected. From the primitive shapes our method can also reconstruct an idealized model that is suitable for use in a CAD system. Categories and Subject Descriptors (according to ACM CCS): Computer Graphics [I.3.5]: Curve, surface, solid, and object representations— 1.
Parallel and Distributed Graph Cuts by Dual Decomposition
, 2010
"... Graph cuts methods are at the core of many stateoftheart algorithms in computer vision due to their efficiency in computing globally optimal solutions. In this paper, we solve the maximum flow/minimum cut problem in parallel by splitting the graph into multiple parts and hence, further increase th ..."
Abstract

Cited by 25 (3 self)
 Add to MetaCart
(Show Context)
Graph cuts methods are at the core of many stateoftheart algorithms in computer vision due to their efficiency in computing globally optimal solutions. In this paper, we solve the maximum flow/minimum cut problem in parallel by splitting the graph into multiple parts and hence, further increase the computational efficacy of graph cuts. Optimality of the solution is guaranteed by dual decomposition, or more specifically, the solutions to the subproblems are constrained to be equal on the overlap with dual variables. We demonstrate that our approach both allows (i) faster processing on multicore computers and (ii) the capability to handle larger problems by splitting the graph across multiple computers on a distributed network. Even though our approach does not give a theoretical guarantee of speedup, an extensive empirical evaluation on several applications with many different data sets consistently shows good performance. An open source implementation of the dual decomposition method is also made publicly available.
A STUDY ON CONTINUOUS MAXFLOW AND MINCUT APPROACHES
"... We propose and investigate novel maxflow models in the spatially continuous setting, with or without supervised constraints, under a comparative study of graph based maxflow / mincut. We show that the continuous maxflow models correspond to their respective continuous mincut models as primal a ..."
Abstract

Cited by 23 (6 self)
 Add to MetaCart
We propose and investigate novel maxflow models in the spatially continuous setting, with or without supervised constraints, under a comparative study of graph based maxflow / mincut. We show that the continuous maxflow models correspond to their respective continuous mincut models as primal and dual problems, and the continuous mincut formulation without supervision constraints regards the wellknown ChanEsedogluNikolova model [15] as a special case. In this respect, basic conceptions and terminologies applied by discrete maxflow / mincut are revisited under a new variational perspective. We prove that the associated nonconvex partitioning problems, unsupervised or supervised, can be solved globally and exactly via the proposed convex continuous maxflow and mincut models. Moreover, we derive novel fast maxflow based algorithms whose convergence can be guaranteed by standard optimization theories. Experiments on image segmentation, both unsupervised and supervised, show that our continuous maxflow based algorithms outperform previous approaches in terms of efficiency and accuracy.
Anisotropic Minimal Surfaces Integrating Photoconsistency and Normal Information for Multiview Stereo
 In European Conference on Computer Vision
, 2010
"... Abstract. In this work the weighted minimal surface model traditionally used in multiview stereo is revisited. We propose to generalize the classical photoconsistencyweighted minimal surface approach by means of an anisotropic metric which allows to integrate a specified surface orientation into th ..."
Abstract

Cited by 16 (4 self)
 Add to MetaCart
(Show Context)
Abstract. In this work the weighted minimal surface model traditionally used in multiview stereo is revisited. We propose to generalize the classical photoconsistencyweighted minimal surface approach by means of an anisotropic metric which allows to integrate a specified surface orientation into the optimization process. In contrast to the conventional isotropic case, where all spatial directions are treated equally, the anisotropic metric adaptively weights the regularization along different directions so as to favor certain surface orientations over others. We show that the proposed generalization preserves all properties and globality guarantees of continuous convex relaxation methods. We make use of a recently introduced efficient primaldual algorithm to solve the arising saddle point problem. In multiple experiments on real image sequences we demonstrate that the proposed anisotropic generalization allows to overcome oversmoothing of smallscale surface details, giving rise to more precise reconstructions. 1
Parallel graphcuts by adaptive bottomup merging
 In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
, 2010
"... Graphcuts optimization is prevalent in vision and graphics problems. It is thus of great practical importance to parallelize the graphcuts optimization using today’s ubiquitous multicore machines. However, the current best serial algorithm by Boykov and Kolmogorov [4] (called the BK algorithm) ..."
Abstract

Cited by 15 (0 self)
 Add to MetaCart
(Show Context)
Graphcuts optimization is prevalent in vision and graphics problems. It is thus of great practical importance to parallelize the graphcuts optimization using today’s ubiquitous multicore machines. However, the current best serial algorithm by Boykov and Kolmogorov [4] (called the BK algorithm) still has the superior empirical performance. It is nontrivial to parallelize as expensive synchronization overhead easily offsets the advantage of parallelism. In this paper, we propose a novel adaptive bottomup approach to parallelize the BK algorithm. We first uniformly partition the graph into a number of regularlyshaped disjoint subgraphs and process them in parallel, then we incrementally merge the subgraphs in an adaptive way to obtain the global optimum. The new algorithm has three benefits: 1) it is more cachefriendly within smaller subgraphs; 2) it keeps balanced workloads among computing cores; 3) it causes little overhead and is adaptable to the number of available cores. Extensive experiments in common applications such as 2D/3D image segmentations and 3D surface fitting demonstrate the effectiveness of our approach. 1.
State of the Art in Surface Reconstruction from Point Clouds
 In Proc. Eurographics 2014
, 2014
"... HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte p ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
(Show Context)
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.