GPU Accelerated Image Registration in Two and Three Dimensions
暂无分享,去创建一个
Medical image registration tasks of large volume datasets, especially in the non-rigid case, often put a heavy burden on computing resources. GPUs are a promising new approach to address computational intensive image processing tasks. We investigate recently introduced GPU hardware features that accelerate 2D and 3D rigid and nonrigid registration tasks. Our implementation is entirely GPU based.
[1] Martin Rumpf,et al. Image Registration by a Regularized Gradient Flow. A Streaming Implementation in DX9 Graphics Hardware , 2004, Computing.
[2] Nicholas Ayache,et al. Grid-Enabled Non-Rigid Registration Of Medical Images , 2004, Parallel Process. Lett..
[3] Christopher Nimsky,et al. Non-rigid Registration with Use of Hardware-Based 3D Bézier Functions , 2002, MICCAI.
[4] U. Clarenz,et al. Towards fast non-rigid registration , 2003 .