AI RESEARCH

Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing

arXiv CS.LG

ArXi:2603.05761v1 Announce Type: new Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a challenge. Current approaches bifurcate into inversion-based guidance, which suffers from "geometric locking" by rigidly adhering to the source trajectory, and posterior sampling approximations (e.g., DPS), which are computationally expensive and unstable.