AI RESEARCH
Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration
arXiv CS.CV
•
ArXi:2603.03648v2 Announce Type: replace Face restoration can be formulated as a continuous-time transformation between image distributions via Flow Matching (FM). However, standard FM typically employs independent coupling, ignoring the statistical correlation between low-quality (LQ) and high-quality (HQ) data. This leads to intersecting trajectories and high velocity-field curvature, requiring multi-step integration. We propose Shortcut-constrained Coupling Flow for Face Restoration (SCFlowFR) to address these challenges.