An Experimental Comparison of Discrete and Continuous Shape Optimization Methods

Authors:
Maria Klodt;Thomas Schoenemann;Kalin Kolev;Marek Schikora;Daniel Cremers
Affiliations:
Department of Computer Science, University of Bonn, Germany;Department of Computer Science, University of Bonn, Germany;Department of Computer Science, University of Bonn, Germany;Department of Computer Science, University of Bonn, Germany;Department of Computer Science, University of Bonn, Germany
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Year:
2008

Citing 19
Cited 17

Visual reconstruction

Visual reconstruction
A new approach to the maximum-flow problem

Journal of the ACM (JACM)
Beyond the flow decomposition barrier

Journal of the ACM (JACM)
Theoretical Improvements in Algorithmic Efficiency for Network Flow Problems

Journal of the ACM (JACM)
Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Globally Optimal Regions and Boundaries as Minimum Ratio Weight Cycles

IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
Markov Random Fields with Efficient Approximations

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Gradient flows and geometric active contour models

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Geodesic active contours

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Computing Geodesics and Minimal Surfaces via Graph Cuts

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-View Stereo via Volumetric Graph-Cuts

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Energy Minimization via Graph Cuts: Settling What is Possible

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
What Metrics Can Be Approximated by Geo-Cuts, Or Global Optimization of Length/Area and Flux

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Globally Minimal Surfaces by Continuous Maximal Flows

IEEE Transactions on Pattern Analysis and Machine Intelligence
Continuous global optimization in multiview 3D reconstruction

EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Total variation minimization and a class of binary MRF models

EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Variational principles, surface evolution, PDEs, level set methods, and the stereo problem

IEEE Transactions on Image Processing

Non-parametric Single View Reconstruction of Curved Objects Using Convex Optimization

Proceedings of the 31st DAGM Symposium on Pattern Recognition
Tracking as Segmentation of Spatial-Temporal Volumes by Anisotropic Weighted TV

EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Global Optimal Multiple Object Detection Using the Fusion of Shape and Color Information

EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Convex relaxation for multilabel problems with product label spaces

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Global Minimization for Continuous Multiphase Partitioning Problems Using a Dual Approach

International Journal of Computer Vision
A variational approach to vesicle membrane reconstruction from fluorescence imaging

Pattern Recognition
Global relabeling for continuous optimization in binary image segmentation

EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Space-varying color distributions for interactive multiregion segmentation: discrete versus continuous approaches

EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
SlimCuts: graphcuts for high resolution images using graph reduction

EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
Parallel and distributed vision algorithms using dual decomposition

Computer Vision and Image Understanding
Global Solutions of Variational Models with Convex Regularization

SIAM Journal on Imaging Sciences
Silhouette-Based variational methods for single view reconstruction

Proceedings of the 2010 international conference on Video Processing and Computational Video
Smooth Chan-Vese segmentation via graph cuts

Pattern Recognition Letters
A Linear Framework for Region-Based Image Segmentation and Inpainting Involving Curvature Penalization

International Journal of Computer Vision
Wehrli 2.0: an algorithm for "tidying up art"

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Vertebral body segmentation in MRI via convex relaxation and distribution matching

MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Optimality Bounds for a Variational Relaxation of the Image Partitioning Problem

Journal of Mathematical Imaging and Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shape optimization is a problem which arises in numerous computer vision problems such as image segmentation and multiview reconstruction. In this paper, we focus on a certain class of binary labeling problems which can be globally optimized both in a spatially discrete setting and in a spatially continuous setting. The main contribution of this paper is to present a quantitative comparison of the reconstruction accuracy and computation times which allows to assess some of the strengths and limitations of both approaches. We also present a novel method to approximate length regularity in a graph cut based framework: Instead of using pairwise terms we introduce higher order terms. These allow to represent a more accurate discretization of the L2-norm in the length term.