Thuerck, DanielWaechter, MichaelWidmer, SvenBuelow, Max vonSeemann, PatrickPfetsch, Marc E.Goesele, MichaelUlf Assarsson and Warren Hunt2016-06-172016-06-172016978-3-03868-008-62079-8679https://doi.org/10.2312/hpg.20161203Given the increasing availability of high-resolution input data, today's computer vision problems tend to grow beyond what has been considered tractable in the past. This is especially true for Markov Random Fields (MRFs), which have expanded beyond millions of variables with thousands of labels. Such MRFs pose new challenges for inference, requiring massively parallel solvers that can cope with large-scale problems and support general, irregular input graphs. We propose a block coordinate descent based solver for large MRFs designed to exploit many-core hardware such as recent GPUs. We identify tree-shaped subgraphs as a block coordinate scheme for irregular topologies and optimize them efficiently using dynamic programming. The resulting solver supports arbitrary MRF topologies efficiently and can handle arbitrary, dense or sparse label sets as well as label cost functions. Together with two additional heuristics for further acceleration, our solver performs favorably even compared to modern specialized solvers in terms of speed and solution quality, especially when solving very large MRFs.I.4.m [Image Processing and Computer Vision]MiscellaneousProbabilistic Models10.2312/hpg.20161203173-183