Uncertainty-Aware Null Space Networks for Data-Consistent Image Reconstruction. (arXiv:2304.06955v1 [cs.CV])

Reconstructing an image from noisy and incomplete measurements is a central
task in several image processing applications. In recent years,
state-of-the-art reconstruction methods have been developed based on recent
advances in deep learning. Especially for highly underdetermined problems,
maintaining data consistency is a key goal. This can be achieved either by
iterative network architectures or by a subsequent projection of the network
reconstruction. However, for such approaches to be used in safety-critical
domains such as medical imaging, the network reconstruction …

applications architectures art arxiv consistent data deep learning image image processing imaging iterative medical medical imaging network networks null processing projection safety safety-critical space state uncertainty