Supplementary Material: Adaptive and Move Making Auxiliary Cuts for Binary Pairwise Energies

نویسندگان

  • Lena Gorelick
  • Yuri Boykov
  • Olga Veksler
چکیده

Below please find supplementary materials for our paper. First, we restate the optimization problem in Sec. 1. Because for some applications below it is more convenient to use a different form of energy, we show how to transform between the different formulations in Sec. 2. We then provide full technical details for two applications: Multi-Region and Compact shape prior in Sections 3.1 and 3.2 respectively. Finally, we provide additional experiments for the squared curvature regularization in Sec. 3.3, which were mentioned but not shown in the paper due to the lack of space.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Tiered Move-making Algorithm for General Non-submodular Pairwise Energies

A large number of problems in computer vision can be modelled as energy minimization problems in a Markov Random Field (MRF) or Conditional Random Field (CRF) framework. Graph-cuts based α-expansion is a standard movemaking method to minimize the energy functions with submodular pairwise terms. However, certain problems require more complex pairwise terms where the α-expansion method is general...

متن کامل

Pseudo-bound Optimization for Binary Energies

High-order and non-submodular pairwise energies are important for image segmentation, surface matching, deconvolution, tracking and other computer vision problems. Minimization of such energies is generally NP-hard. One standard approximation approach is to optimize an auxiliary function an upper bound of the original energy across the entire solution space. This bound must be amenable to fast ...

متن کامل

Supplementary Material Accompanying ‘Geometry Driven Semantic Labeling of Indoor Scenes’

In this appendix, we will show how the higher order energy potentials can be minimized using graph cuts. Since, graph cuts can efficiently minimize submodular functions, we will transform our higher order energy function (Eq. 9) to a submodular second order energy function. For the case of both αβ-swap and αexpansion move making algorithms, we will explain this transformation and the process of...

متن کامل

Submodularization for Quadratic Pseudo-Boolean Optimization

Many computer vision problems require optimization of binary non-submodular energies. We propose a general optimization framework based on local submodular approximations (LSA). Unlike standard LP relaxation methods that linearize the whole energy globally, our approach iteratively approximates the energies locally. On the other hand, unlike standard local optimization methods (e.g. gradient de...

متن کامل

Using Hybrid Fuzzy PROMETHEE II and Fuzzy Binary Goal Programming for Risk Ranking: A Case Study of Highway Construction Projects

Multi attribute decision making methods are considered as one of the most useful methods for solving ranking problems. In some decision making problems, while the alternatives for corresponding criteria are compared in a pairwise comparison manner, if the criteria are inherently fuzzy, debates will arise in ranking alternatives due to the closeness of the values of the criteria. In this researc...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017