no code implementations • 2 Apr 2019 • Amirkoushyar Ziabari, Michael Kirka, Vincent Paquit, Philip Bingham, Singanallur Venkatakrishnan
We then train a 2. 5D deep convolutional neural network [4], deemed 2. 5D Deep Learning MBIR (2. 5D DL-MBIR), on these pairs of noisy and high-quality 3D volumes to learn a fast, non-linear mapping function.