Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
This addresses a key optimization problem for computer vision researchers working with MRFs, offering an incremental improvement over existing techniques.
The paper tackles the optimization difficulty of multi-label MRFs with non-convex priors in computer vision by introducing an iterative algorithm that approximates the energy with a weighted surrogate, guaranteeing energy decrease at each step and enabling handling of various non-convex priors via graph cuts, with demonstrated benefits over state-of-the-art methods on stereo and inpainting problems.
While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize. To tackle this, we introduce an algorithm that iteratively approximates the original energy with an appropriately weighted surrogate energy that is easier to minimize. Our algorithm guarantees that the original energy decreases at each iteration. In particular, we consider the scenario where the global minimizer of the weighted surrogate energy can be obtained by a multi-label graph cut algorithm, and show that our algorithm then lets us handle of large variety of non-convex priors. We demonstrate the benefits of our method over state-of-the-art MRF energy minimization techniques on stereo and inpainting problems.