A few weeks ago, we published a blog entry that demonstrated the ability of Jacket to speed up “compressive sensing”, a technology that has wide applications in areas such as Image processing, reconstruction and spectroscopy. Here, we discuss the work of Nabor Reyna Jr. and Wotao Yin from Rice University using Jacket to speed up “compressive sensing” algorithms in reconstruction.
This work deals with reconstruction of signals using partial Fourier matrices (RecPF). The major computational components of the algorithm involve shrinkage and FFTs. Jacket is employed to accelerate this compute-heavy code, and the resultant version (gRecPF) was about 5x faster!
To reduce the cost involved in generating the random matrices involved in the above method, a second method (RecPC) that employed Circulant matrices in place of the Fourier matrices was developed. A Jacket version of the same was also implemented (gRecPC) and this led to a 3X speedup!
Here are some sample reconstructed images using gRecPC
MRI Image Reconstruction using 20% sample mask
Reconstructed Image of Great Wall of China using 30% partial circulant samples
A more detailed summary of the work may be found here and here. We thank Nabor Reyna and Wotao Yin from Rice University for exploring Jacket as a solution to important computational problems of today, and look forward to hearing more from them as they continue this line of research!