Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts

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.
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download

Contributor : Nicolas Bonneel <>
Submitted on : Thursday, January 28, 2016 - 5:15:14 PM
Last modification on : Wednesday, April 3, 2019 - 1:08:13 AM
Long-term archiving on : Friday, April 29, 2016 - 10:21:44 AM


Files produced by the author(s)


  • HAL Id : hal-01264120, version 1


M Keuper, E Levinkov, Nicolas Bonneel, Guillaume Lavoué, T Brox, et al.. Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts. The IEEE International Conference on Computer Vision (ICCV), Dec 2015, Santiago, Chile. 9 p. ⟨hal-01264120⟩



Record views


Files downloads