Iterative optimization methods for effiecient image restoration on multicore architectures

This paper explores effective algorithms for the solution of numerical nonlinear optimization problems in image restoration. The technology of modern acquisition techniques and devices most often returns data of increasing size, so we focus on the Scaled Gradient Projection algorithm, which is well suited to large-scale applications. We present its parallel implementations on different hardware, namely Tesla-series GPUs and cluster of last-generation multi-core CPUs. Algorithm and codes are tested against both 2D and 3D meaningful real-world problems