2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
Tatsunori Taniai , University of Tokyo, Japan
Yasuyuki Matsushita , Osaka University, Japan
Takeshi Naemura , University of Tokyo, Japan
We propose an efficient and general purpose energy optimization method for binary variable energies used in various low-level vision tasks. Our method can be used for broad classes of higher-order and pairwise non-submodular functions. We first revisit a submodular-supermodular procedure (SSP) , 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 [2, 9, 25]. In the experiments, we apply our method to image segmentation, deconvolution, and binarization, and show improvements over state-of-the-art methods.
Tatsunori Taniai, Yasuyuki Matsushita, Takeshi Naemura, "Superdifferential cuts for binary energies", 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 00, no. , pp. 2030-2038, 2015, doi:10.1109/CVPR.2015.7298814