کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
526063 | 869057 | 2011 | 12 صفحه PDF | دانلود رایگان |
![عکس صفحه اول مقاله: Parallel and distributed vision algorithms using dual decomposition Parallel and distributed vision algorithms using dual decomposition](/preview/png/526063.png)
We investigate dual decomposition approaches for optimization problems arising in low-level vision. Dual decomposition can be used to parallelize existing algorithms, reduce memory requirements and to obtain approximate solutions of hard problems. An extensive set of experiments are performed for a variety of application problems including graph cut segmentation, curvature regularization and more generally the optimization of MRFs. We demonstrate that the technique can be useful for desktop computers, graphical processing units and supercomputer clusters. To facilitate further research, an implementation of the decomposition methods is made publicly available.
► Parallel minimum cut using dual decomposition.
► MRF inference on graphical processing units.
► Parallel inference for general MRFs.
Journal: Computer Vision and Image Understanding - Volume 115, Issue 12, December 2011, Pages 1721–1732