Fast, Approximately Optimal Solutions for Single and Dynamic MRFs

A new efficient MRF optimization algorithm, called FastPD, is proposed, which generalizes -expansion. One of its main advantages is that it offers a substantial speedup over that method, e.g. it can be at least 3-9 times faster than -expansion. Its efficiency is a result of the fact that Fast-PD exploits information coming not only from the original MRF problem, but also from a dual problem. Furthermore, besides static MRFs, it can also be used for boosting the performance of dynamic MRFs, i.e. MRFs varying over time. On top of that, Fast-PD makes no compromise about the optimality of its solutions: it can compute exactly the same answer as -expansion, but, unlike that method, it can also guarantee an almost optimal solution for a much wider class of NP-hard MRF problems. Results on static and dynamic MRFs demonstrate the algorithm's efficiency and power. E.g., Fast-PD has been able to compute disparity for stereoscopic sequences in real time, with the resulting disparity coincid...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Nikos Komodakis, Georgios Tziritas, Nikos Paragios
• Keywords: Computer Vision, CVPR 2007, Dynamic Mrfs, MRF Optimization Algorithm, Np-hard Mrf Problems, Original Mrf Problem, Substantial Speedup