Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts
Authors:
Preprint
Abstract
Formulations of the Image Decomposition Problem 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 design and implement two efficient algorithms (primal feasible heuristics) for the MP and LMP which allow us to study instances of both problems w.r.t. the pixel grid graphs of the images in the BSDS-500 benchmark. The decompositions we obtain do not differ significantly from the state of the art, suggesting that the LMP is a competitive formulation of the Image Decomposition Problem. To demonstrate the generality of the LMP, we apply it also to the Mesh Decomposition Problem posed by the Princeton benchmark, obtaining state-of-the-art decompositions.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Probabilistic Correlation Clustering and Image Partitioning Using Perturbed Multicuts2015
- Hierarchical Planar Correlation Clustering for Cell Segmentation2015
- Crisp Boundary Detection Using Pointwise Mutual Information2014
- Segmenting Planar Superpixel Adjacency Graphs w.r.t. Non-planar Superpixel Affinity GraphsLecture Notes in Computer Science, 2013
- Globally Optimal Closed-Surface Segmentation for Connectomics2012
- Fast Planar Correlation Clustering for Image Segmentation2012
- Globally Optimal Image Partitioning by Multicuts2011
- Consistent mesh partitioning and skeletonisation using the shape diameter functionThe Visual Computer, 2008
- Geometry of Cuts and Metrics1997
- An Efficient Heuristic Procedure for Partitioning GraphsBell System Technical Journal, 1970