🛰️ Daily AI Frontier
‹ back to 2026-07-24

SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion

arXiv cs.CV Multimodal & Generative Wenbin Duan, Yan Shu, Zhuoyuan Fu, Fangmin Zhao, Yan Li, Yaru Zhao, Binyang Li 2026-07-23

TL;DR - SlerpFlow is a zero-shot geometric correction method for fast, high-fidelity inversion and editing with FLUX rectified-flow models. It preserves first-order Euler efficiency while improving reconstruction fidelity and semantic alignment without additional training.

  • Uses spherical linear interpolation to align flow velocities with latent-space curvature.
  • Treats trajectory curvature as necessary for remaining on the data manifold, rather than as numerical error.
  • Caches corrected velocities for subsequent steps, avoiding complex high-order approximations.
  • Experiments cover FLUX-based image reconstruction and semantic editing.

view merged work →