Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts

  title={Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts},
  author={Margret Keuper and Evgeny Levinkov and Nicolas Bonneel and Guillaume Lavou{\'e} and Thomas Brox and Bjoern Andres},
Formulations of the Image Decomposition Problem [18] as a Multicut Problem (MP) w.r.t. a superpixel graph have received considerable attention. In contrast, instances of the MP w.r.t. a pixel grid graph have received little attention, firstly, because the MP is NP-hard and instances w.r.t. a pixel grid graph are hard to solve in practice, and, secondly, due to the lack of long-range terms in the objective function of the MP. We propose a generalization of the MP with long-range terms (LMP). We… 

Figures and Tables from this paper

Higher-Order Multicuts for Geometric Model Fitting and Motion Segmentation.
This paper proposes a pseudo-boolean formulation for a multiple model fitting problem based on a formulation of any-order minimum cost lifted multicuts, which allows to partition an undirected graph with pairwise connectivity such as to minimize costs defined over any set of hyper-edges.
Solving Minimum Cost Lifted Multicut Problems by Node Agglomeration
This work proposes two variants of a heuristic solver (primal feasible heuristic), which greedily generate solutions within a bounded amount of time for the minimum cost lifted multicut problem.
A Benders Decomposition Approach to Correlation Clustering
  • Jovita Lukasik, Margret Keuper, M. Singh, Julian Yarkony
  • Computer Science
    2020 IEEE/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC) and Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S)
  • 2020
The Benders decomposition approach provides a promising new avenue to accelerate optimization for CC, and, in contrast to previous cutting plane approaches, theoretically allows for massive parallelization.
Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation
It is argued that the access to such uncertainties is crucial for many practical applications and an evaluation by means of sparsifications on three different, widely used datasets in the context of image decomposition and motion segmentation in terms of variation of information and Rand index is conducted.
The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning
The Mutex Watershed is proposed, an efficient algorithm for graph partitioning that can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold.
Optimizing Edge Detection for Image Segmentation with Multicut Penalties
It is argued that such formulation of a Minimum Cost Multicut Problem, while providing a first step towards end-to-end learnable edge weights, is suboptimal, since it is built upon a loose relaxation of the MP.
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications
We state a combinatorial optimization problem whose feasible solutions define both a decomposition and a node labeling of a given graph. This problem offers a common mathematical abstraction of
The Mutex Watershed: Efficient, Parameter-Free Image Partitioning
When presented with short-range attractive and long-range repulsive cues from a deep neural network, the Mutex Watershed gives results that currently define the state-of-the-art in the competitive ISBI 2012 EM segmentation benchmark.
An Efficient Fusion Move Algorithm for the Minimum Cost Lifted Multicut Problem
This work proposes a fusion move algorithm for computing feasible solutions, better and more efficiently than existing algorithms, and demonstrates this and applications to image segmentation, obtaining a new state of the art for a problem in biological image analysis.
Massively Parallel Benders Decomposition for Correlation Clustering
The Benders decomposition approach provides a promising new avenue to accelerate optimization for CC, and allows for massive parallelization.


Cut, Glue, & Cut: A Fast, Approximate Solver for Multicut Partitioning
The proposed algorithm finds segmentations that, as measured by a loss function, are as close to the ground-truth as the global optimum found by exact solvers, which is important for large-scale problems.
Higher-order segmentation via multicuts
Segmenting Planar Superpixel Adjacency Graphs w.r.t. Non-planar Superpixel Affinity Graphs
This work considers minimum multicuts of superpixel affinity graphs in which all affinities between non-adjacent superpixels are negative and proposes a relaxation by Lagrangian decomposition and a constrained set of re-parameterizations for which it can optimize exactly and efficiently.
Variational mesh decomposition
A variational mesh decomposition algorithm that can efficiently partition a mesh into a prescribed number of segments is presented that outperforms competitive segmentation methods when evaluated on the Princeton Segmentation Benchmark.
Image Segmentation UsingHigher-Order Correlation Clustering
The proposed higher-order correlation clustering (HO-CC) framework is formulated in a supervised manner for many high-level computer vision tasks to consider short- and long-range dependency among various regions of an image and also to incorporate wider selection of features.
Consistent mesh partitioning and skeletonisation using the shape diameter function
This paper considers mesh partitioning and skeletonisation on a wide variety of meshes, and bases its algorithms on a volume-based shape-function called the shape-diameter-function (SDF), which remains largely oblivious to pose changes of the same object and maintains similar values in analogue parts of different objects.
Probabilistic image segmentation with closedness constraints
We propose a novel graphical model for probabilistic image segmentation that contributes both to aspects of perceptual grouping in connection with image segmentation, and to globally optimal
Mesh Segmentation with Concavity-Aware Fields
This paper presents a simple and efficient automatic mesh segmentation algorithm that solely exploits the shape concavity information and employs a score-based greedy algorithm to select the best cuts.
Learning 3D mesh segmentation and labeling
This paper presents a data-driven approach to simultaneous segmentation and labeling of parts in 3D meshes, formulated as a Conditional Random Field model, with terms assessing the consistency of faces with labels, and terms between labels of neighboring faces.
Higher-Order Correlation Clustering for Image Segmentation
Experimental results on various datasets show that the proposed higher-order correlation clustering outperforms other state-of-the-art image segmentation algorithms.