AI RESEARCH
Single-Subject Multi-View MRI Super-Resolution via Implicit Neural Representations
arXiv CS.CV
•
ArXi:2603.22627v1 Announce Type: cross Clinical MRI frequently acquires anisotropic volumes with high in-plane resolution and low through-plane resolution to reduce acquisition time. Multiple orientations are therefore acquired to provide complementary anatomical information. Conventional integration of these views relies on registration followed by interpolation, which can degrade fine structural details. Recent deep learning-based super-resolution (SR) approaches have nstrated strong performance in enhancing single-view images.