1 code implementation • ICCV 2023 • Berk Iskender, Marc L. Klasky, Yoram Bresler
In particular, in the case of dynamic tomography, only a single projection at a single view angle may be available at a time, making the problem severely ill-posed.
no code implementations • 21 Mar 2021 • Berk Iskender, Yoram Bresler
Different from previous works, they incorporate both an initial reconstruction of the object of interest and the scatter-corrupted measurements related to it, and use a deep neural network architecture and cost function, both specifically tailored to the problem.
no code implementations • 21 Apr 2022 • Berk Iskender, Marc L. Klasky, Yoram Bresler
In dynamic tomography the object undergoes changes while projections are being acquired sequentially in time.
no code implementations • 11 Oct 2022 • Berk Iskender, Zhenlin Xu, Simon Kornblith, En-Hung Chu, Maryam Khademi
Many contrastive representation learning methods learn a single global representation of an entire image.