Fast MRF Optimization with Application to Depth Reconstruction

  title={Fast MRF Optimization with Application to Depth Reconstruction},
  author={Qifeng Chen and Vladlen Koltun},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
We describe a simple and fast algorithm for optimizing Markov random fields over images. The algorithm performs block coordinate descent by optimally updating a horizontal or vertical line in each step. While the algorithm is not as accurate as state-of-the-art MRF solvers on traditional benchmark problems, it is trivially parallelizable and produces competitive results in a fraction of a second. As an application, we develop an approach to increasing the accuracy of consumer depth cameras. The… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS