Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction

arXiv:2404.19075v1 Announce Type: cross
Abstract: 4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an extremely ill-posed inverse problem. Existing approaches assume that the object remains static for the duration of several tens or hundreds of X-ray projection measurement images (reconstruction of consecutive limited-angle CT scans). However, this is an unrealistic assumption for many in-situ experiments that causes spurious artifacts and inaccurate morphological reconstructions of the object. To solve this problem, we propose to …

abstract arxiv cs.ai cs.cv cs.lg cs.na distributed dynamic eess.iv events images math.na measurement network object objects optimization projection ray representation space stochastic type x-ray x-ray computed tomography