AI RESEARCH
GraphMAR: Geometry-Aware Graph Learning Framework for Spatially Adaptive CT Metal Artifact Reduction
arXiv CS.CV
•
ArXi:2605.17343v1 Announce Type: new Computed tomography (CT) metal artifact reduction (MAR) aims to reduce the severe streaking artifacts induced by metallic implants and other high-density objects. Effective MAR generally requires both accurate artifact localization and artifact removal. Sinogram-domain methods can exploit explicit geometric cues, such as metal traces, to identify metal-corrupted measurements, while requiring raw projection data, which is often unavailable in clinical and practical scenarios.