AI RESEARCH
Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance
arXiv CS.CV
•
ArXi:2603.11509v1 Announce Type: new Classifier-Free Guidance (CFG) serves as the de facto control mechanism for conditional diffusion, yet high guidance scales notoriously induce oversaturation, texture artifacts, and structural collapse. We attribute this failure to a geometric mismatch: standard CFG performs Euclidean extrapolation in ambient space, inadvertently driving sampling trajectories off the high-density data manifold. To resolve this, we present Manifold-Optimal Guidance (MOG), a framework that reformulates guidance as a local optimal control problem.