Superdifferential Cuts for Binary Energies

Tatsunori Taniai, Yasuyuki Matsushita, Takeshi Naemura

CVPR 2015

doi:10.1109/CVPR.2015.7298814 /cvpr/2015/taniai2015cvpr-superdifferential/

Abstract

We propose an efficient and general purpose energy optimization method for binary variable energies used in various low-level vision tasks. The proposed method can be used for broad classes of higher-order and pairwise non-submodular functions. We first revisit a submodular-supermodular procedure (SSP) [Narasimhan05], which is previously studied for higher-order energy optimization. We then present our method as generalization of SSP, which is further shown to generalize several state-of-the-art techniques for higher-order and pairwise non-submodular functions [Ayed13, Gorelick14, Tang14]. In the experiments, we apply our method to image segmentation, deconvolution, and binarization, and show improvements over state-of-the-art methods.

PDF CVPR Semantic Scholar

Cite

Text

Taniai et al. "Superdifferential Cuts for Binary Energies." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298814

Markdown

[Taniai et al. "Superdifferential Cuts for Binary Energies." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/taniai2015cvpr-superdifferential/) doi:10.1109/CVPR.2015.7298814

BibTeX

@inproceedings{taniai2015cvpr-superdifferential,
  title     = {{Superdifferential Cuts for Binary Energies}},
  author    = {Taniai, Tatsunori and Matsushita, Yasuyuki and Naemura, Takeshi},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298814},
  url       = {https://mlanthology.org/cvpr/2015/taniai2015cvpr-superdifferential/}
}