Continuous Maximal Flows and Wulff Shapes: Application to MRFs

Convex and continuous energy formulations for low level vision problems enable efficient search procedures for the corresponding globally optimal solutions. In this work we extend the well-established continuous, isotropic capacitybased maximal flow framework to the anisotropic setting. By using powerful results from convex analysis, a very simple and efficient minimization procedure is derived. Further, we show that many important properties carry over to the new anisotropic framework, e.g. globally optimal binary results can be achieved simply by thresholding the continuous solution. In addition, we unify the anisotropic continuous maximal flow approach with a recently proposed convex and continuous formulation for Markov random fields, thereby allowing more general smoothness priors to be incorporated. Dense stereo results are included to illustrate the capabilities of the proposed approach.

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Christopher Zach (UNC Chapel Hill), Marc Niethammer (UNC Chapel Hill), Jan-Michael Frahm (UNC Chapel Hill)
• Keywords: AndWulff Shapes, Computer Vision, Continuous Maximal Flows, CVPR 2009, Markov Random Fields (MRF)