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 ...
We propose a global optimization framework for 3D shape reconstruction from sparse noisy 3D measurements frequently encountered in range scanning, sparse featurebased stereo, and ...
Two challenges in computer vision are to accommodate noisy data and missing data. Many problems in computer vision, such as segmentation, filtering, stereo, reconstruction, inpain...
— A novel parallel approach to run standard particle swarm optimization (SPSO) on Graphic Processing Unit (GPU) is presented in this paper. By using the general-purpose computing...