AI RESEARCH
Improving Image-to-Image Translation via a Rectified Flow Reformulation
arXiv CS.CV
•
ArXi:2603.20186v1 Announce Type: new In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regression networks as continuous-time transport models. While pixel-wise I2I regression is simple, stable, and easy to adapt across tasks, it often over-smooths ill-posed and multimodal targets, whereas generative alternatives often require additional components, task-specific tuning, and complex