Publications in the field of Image and Video Segmentation:



  Bilevel Optimization with Nonsmooth Lower Level Problems paper              
  Peter Ochs, Rene Ranftl, Thomas Brox, Thomas Pock       SSVM 2015 (Preprint)  
paper We consider a bilevel optimization approach for parameter learning in nonsmooth variational models. Existing approaches solve this problem by applying implicit differentiation to a sufficiently smooth approximation of the nondifferentiable lower level problem. We propose an alternative method based on differentiating the iterations of a nonlinear primal-dual algorithm. Our method computes exact (sub)gradients and can be applied also in the nonsmooth setting. We show preliminary results for the case of multi-label image segmentation.
Show Details Download Paper   (Downloads: 39277)


  A Deep Variational Model for Image Segmentation paper           links  
  Rene Ranftl, Thomas Pock       GCPR 2014  
paper In this paper we introduce a novel model that combines Deep Convolutional Neural Networks with a global inference model. Our model is derived from a convex variational relaxation of the minimum s-t cut problem on graphs, which is frequently used for the task of image segmentation. We treat the outputs of Convolutional Neural Networks as the unary and pairwise potentials of a graph and derive a smooth approximation to the minimum s-t cut problem. During training, this approximation facilitates the adaptation of the Convolutional Neural Network to the smoothing that is induced by the global model.
Show Details Download Paper   (Downloads: 95770)


  A Convex, Lower Semi-Continuous Approximation of Euler's Elastica energy paper              
  Kristian Bredies, Thomas Pock, Benedikt Wirth       Preprint  
paper We propose a convex, lower semi-continuous, coercive approximation of Euler's elastica energy for images, which is thus very well-suited as a regularizer in image processing. The approximation is not quite the convex relaxation, and we discuss its close relation to the exact convex relaxation as well as the difficulties associated with computing the latter. Interestingly, the convex relaxation of the elastica energy reduces to constantly zero if the total variation part of the elastica energy is neglected.
Show Details Download Paper   (Downloads: 171705)
  An iterated l1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision paper              
  Peter Ochs, Alexey Dosovitskiy, Thomas Brox, Thomas Pock       CVPR 2013  
paper Natural image statistics indicate that we should use non-convex norms for most regularization tasks in image processing and computer vision. Still, they are rarely used in practice due to the challenge to optimize them. Recently, iteratively reweighed l1 minimization has been proposed as a way to tackle a class of non-convex functions by solving a sequence of convex l2 - l1 problems. Here we extend the problem class to linearly constrained optimization of a Lipschitz continuous function, which is the sum of a convex function and a function being concave and increasing on the non-negative orthant (possibly non-convex and non-concave on the whole space).
Show Details Download Paper   (Downloads: 222785)


  Convex Optimization for Image Segmentation paper              
  Markus Unger       Phd Thesis 2012  
paper Segmentation is one of the fundamental low level problems in computer vision. Extracting objects from an image gives rise to further high level processing as well as image composing. A segment not always has to correspond to a real world object, but can fulfill any coherency criterion (e.g. similar motion). Segmentation is a highly ambiguous task, and usually requires some prior knowledge. This can either be obtained by interactive user input in an supervised manner, or completely unsupervised using strong prior knowledge. In this thesis we use continuous energy minimization to tackle all of these problems.
Show Details Download Paper   (Downloads: 172296)
  Approximate Envelope Minimization for Curvature Regularity paper              
  Stefan Heber, Rene Ranftl, Thomas Pock       Workshop on Higher-Order Models and Global Constraints in Computer Vision, ECCV 2012  
paper We propose a method for minimizing a non-convex function, which can be split up into a sum of simple functions. The key idea of the method is the approximation of the convex envelopes of the simple functions, which leads to a convex approximation of the original function. A solution is obtained by minimizing this convex approximation. Cost functions, which fulfill such a splitting property are ubiquitous in computer vision, ...
Show Details Download Paper   (Downloads: 168579)
  Joint Motion Estimation and Segmentation of Complex Scenes with Label Costs and Occlusion Modeling paper              
  Markus Unger, Manuel Werlberger, Thomas Pock, Horst Bischof       CVPR 2012, Providence, Rhode Island  
paper We propose a unified variational formulation for joint motion estimation and segmentation with explicit occlusion handling. This is done by a multi-label representation of the flow field, where each label corresponds to a parametric representation of the motion. We use a convex formulation of the multi-label Potts model with label costs and show that the asymmetric map-uniqueness criterion can be integrated into our formulation by means of convex constraints.
Show Details Download Paper   (Downloads: 177071)
  A convex approach to minimal partitions (revised version) paper              
  Antonin Chambolle, Daniel Cremers, Thomas Pock       SIAM Journal on Imaging Sciences  
paper We describe a convex relaxation for a family of problems of minimal perimeter partitions. The minimization of the relaxed problem can be tackled numerically, we describe an algorithm and show some results. In most cases, our relaxed problem finds a correct numerical approximation of the optimal solution.
Show Details Download Paper   (Downloads: 204332)
  Convex relaxation of a class of vertex penalizing functionals paper              
  Kristian Bredies, Thomas Pock, Benedikt Wirth       Journal of Mathematical Imaging and Vision  
paper We investigate a class of variational problems that incorporate in some sense curvature information of the level lines. The functionals we consider incorporate metrics defined on the orientations of pairs of line segments that meet in the vertices of the level lines. We discuss two particular instances: One instance that minimizes the total number of vertices of the level lines and another instance that minimizes the total sum of the absolute exterior angles between the line segments.
Show Details Download Paper   (Downloads: 233061)


  Neural Process Reconstruction from Sparse User Scribbles paper           links  
  Mike Roberts, Won-Ki Jeong, Amelio Vazquez-Reina, Markus Unger, Horst Bischof, Jeff Lichtman, Hanspeter Pfister       Medical Image Computing and Computer Assisted Intervention (MICCAI) 2011  
paper We present a novel semi-automatic method for segmenting neural processes in large, highly anisotropic EM (electron microscopy) image stacks. Our method takes advantage of sparse scribble annotations provided by the user to guide a 3D variational segmentation model, thereby allowing our method to globally optimally enforce 3D geometric constraints on the segmentation.
Show Details Download Paper   (Downloads: 213451)
  Global Relabeling for Continuous Optimization in Binary Image Segmentation paper              
  Markus Unger, Thomas Pock, Horst Bischof       EMMCVPR 2011, Saint Petersburg, Russia  
paper Recently, continuous optimization methods have become quite popular since they can deal with a variety of non-smooth convex problems. They are inherently parallel and therefore well suited for GPU implementations. Most of the continuous optimization approaches have in common that they are very fast in the beginning, but tend to get very slow as the solution gets close to the optimum...
Show Details Download Paper   (Downloads: 209518)
  Efficient Minimization of the Non-Local Potts Model paper              
  Manuel Werlberger, Markus Unger, Thomas Pock, and Horst Bischof       SSVM 2011, Ein-Gedi, Israel  
paper The Potts model is a well established approach to solve different multi-label problems. The classical Potts prior penalizes the total interface length to obtain regular boundaries. Although the Potts prior works well for many problems, it does not preserve fine details of the boundaries.
Show Details Download Paper   (Downloads: 224544)


  Interactive Multi-Label Segmentation paper              
  Jakob Santner       Phd Thesis 2010  
paper Interactive image segmentation deals with partitioning an image into multiple pairwise-disjoint regions based on input provided by a human operator. Being interactive means, that an algorithm has to quickly react on user input, which limits the computational complexity of the employed algorithms drastically. Therefore, many interactive segmentation methods represent these regions with simple models based on low-dimensional feature spaces...
Show Details Download Paper   (Downloads: 237915)
  Interactive Multi-Label Segmentation paper       software      
  Jakob Santner and Thomas Pock and Horst Bischof       Asian Conference on Computer Vision (ACCV) 2010  
paper This paper addresses the problem of interactive multi-label segmentation. We propose a powerful new framework using several color models and texture descriptors, Random Forest likelihood estimation as well as a multi-label Potts-model segmentation. We perform most of the calculations on the GPU and reach runtimes of less than two seconds, allowing for convenient user interaction...
Show Details Download Paper   (Downloads: 212410)


  Segmentation of interwoven 3d tubular tree structures utilizing shape priors and graph cuts paper              
  Christian Bauer, Thomas Pock, Erich Sorantin, Horst Bischof, Reinhard Beichel       Medical Image Analysis  
paper We present and evaluate a general approach for robust segmentation of tubular tree structures in 3d medical images.
Show Details Download Paper   (Downloads: 228380)
  Tracking as Segmentation of Spatial-Temporal Volumes by Anisotropic Weighted TV paper              
  Markus Unger, Thomas Mauthner, Thomas Pock, Horst Bischof       EMMCVPR 2009  
paper Tracking is usually interpreted as finding an object in single consecutive frames. Regularization is done by enforcing temporal smoothness of appearance, shape and motion. We propose a tracker, by interpreting the task of tracking as segmentation of a volume in 3D...
Show Details Download Paper   (Downloads: 299199)
  Interactive Texture Segmentation using Random Forests and Total Variation paper              
  Jakob Santner, Markus Unger, Thomas Pock, Christian Leistner, Amir Saffari, Horst Bischof       British Machine Vision Conference 2009  
paper Common methods for interactive texture segmentation rely on probability maps based on low dimensional features such as e.g. intensity or color, that are usually modeled using basic learning algorithms such as histograms or Gaussian Mixture Models. The use of low level features allows for fast generation of these hypotheses but limits applicability to a small class of images. We address this problem by learning complex descriptors with Random Forests...
Show Details Download Paper   (Downloads: 275655)
  An Algorithm for Minimizing the Mumford-Shah Functional paper              
  Thomas Pock, Daniel Cremers, Horst Bischof, Antonin Chambolle       International Conference on Computer Vision 2009  
paper In this work we revisit the Mumford-Shah functional, one of the most studied variational approaches to image segmentation. The contribution of this paper is to propose an algorithm which allows to minimize a convex relaxation of the Mumford-Shah functional obtained by functional lifting. The algorithm is an efficient primal-dual projection algorithm for which we prove convergence.
Show Details Download Paper   (Downloads: 339860)
  A Variational Model for Interactive Shape Prior Segmentation and Real-Time Tracking paper              
  Manuel Werlberger, Thomas Pock, Markus Unger, Horst Bischof       SSVM 2009, Voss, Norway  
paper In this paper, we introduce a semi-automated segmentation method based on minimizing the Geodesic Active Contour energy incorporating a shape prior. We increase the robustness of the segmentation result using the additional shape information that represents the desired structure. Furthermore the user has the possibility to take corrective actions during the segmentation...
Show Details Download Paper   (Downloads: 276344)
  Semi Automatic Segmentation of Articular Cartilage using Variational Methods paper              
  Christian Reinbacher       Master's Thesis  
paper In this Master's Thesis we propose an interactive segmentation framework for the semi automatic segmentation of articular cartilage. Until today, no automatic segmentation method is able achieve the accuracy, necessary for a trustworthy diagnosis. Also, physicians in general prefer to be able to control and modify the segmentation result, which is usually complicated using automatic methods...
Show Details Download Paper   (Downloads: 266247)
  A Convex Relaxation Approach for Computing Minimal Partitions paper              
  Thomas Pock, Antonin Chambolle, Daniel Cremers, Horst Bischof       CVPR 2009, Miami, FL  
paper In this work we propose a convex relaxation approach for computing minimal partitions. Our approach is based on rewriting the minimal partition problem (also known as Potts model) in terms of a primal dual Total Variation functional. We show that the Potts prior can be incorporated by means of convex constraints on the dual variables. For minimization we propose an efficient primal dual projected gradient algorithm...
Show Details Download Paper   (Downloads: 317539)


  A convex approach for computing minimal partitions paper              
  Antonin Chambolle, Daniel Cremers, Thomas Pock       Technical Report  
paper We describe a convex relaxation for a family of problems of minimal perimeter partitions. The minimization of the relaxed problem can be tackled numerically, we describe an algorithm and show some results. In most cases, our relaxed problem finds a correct...
Show Details Download Paper   (Downloads: 316516)
  TVSeg - Interactive Total Variation Based Image Segmentation paper              
  Markus Unger, Thomas Pock, Werner Trobin, Daniel Cremers, Horst Bischof       British Machine Vision Conference 2008  
paper Interactive object extraction is an important part in any image editing software. We present a two step segmentation algorithm that first obtains a binary segmentation and then applies matting on the border regions to obtain a smooth alpha channel...
Show Details Download Paper   (Downloads: 383276)
  Interactive globally optimal image segmentation paper              
  Markus Unger, Thomas Pock, Horst Bischof       Technical Report 08/02  
paper Image segmentation is a challenging task in computer vision. We present a general purpose image segmentation framework, and focus on its application to medical imaging...
Show Details Download Paper   (Downloads: 406566)
  Globally Optimal TV-L1 Shape Prior Segmentation paper              
  Manuel Werlberger       Master Thesis 2008  
paper Interpreting an image is a common and challenging task in computer vision. A human observer does not only use intensity or color information or other basic features when looking for region boundaries but also takes prior knowledge into account...
Show Details Download Paper   (Downloads: 388083)
  Continuous Globally Optimal Image Segmentation with Local Constraints paper              
  Markus Unger, Thomas Pock, Horst Bischof       Computer Vision Winter Workshop 2008  
paper The Geodesic Active contour model is a very flexible model for variational image segmentation. Unfortunately the Geodesic Active Contour model exhibits local minima making segmentation results strongly dependent on its initialization...
Show Details Download Paper   (Downloads: 399582)
  Fast Total Variation for Computer Vision paper              
  Thomas Pock       Phd Thesis 2008  
paper Motivated by statistical inference methods, variational methods are among the most successful methods to solve a number of different Computer Vision problems. Variational methods aim to minimize an energy functional...
Show Details Download Paper   (Downloads: 512896)


  A Probabilistic Multi-phase Model for Variational Image Segmentation paper              
  Thomas Pock, Horst Bischof       Pattern Recognition (Proc. DAGM) 2006  
paper Recently, the Phase Field Method has shown to be a powerful tool for variational image segmentation. In this paper, we present a novel multi-phase model for probability based image segmentation...
Show Details Download Paper   (Downloads: 392575)