Computer Vision News - August 2022

32 Best Paper MIDL 1st runner-up Tamaz Amiranashvili is a PhD student at the Technical University of Munich, with close ties to the University of Zurich and the Zuse Institute Berlin, under the supervision of Bjoern Menze and Stefan Zachow. His paper exploring the task of reconstructing full or high-resolution shapes from sparse or partial measurements has just won a Best Paper Runner Up award at MIDL 2022. He gives us an insight into why it impressed the judges. Anatomical structures usually have very distinct shapes , and the distribution of shapes that naturally occur within a population can be learned and applied to various tasks in medical imaging. What distinguishes the model described in this paper fromrelatedworks is that it can learn on sparse measurements, particularly LEARNING SHAPE RECONSTRUCTION FROM SPARSE MEASUREMENTS WITH NEURAL IMPLICIT FUNCTIONS