Preprint
Aug 2026
Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
A novel optimizer-corrector framework that alternates between gradient steps for objective minimization and guided flow matching to drive the latent state back to the valid shape manifold is introduced, preserving geometric validity without sacrificing expressiveness while remaining computationally feasible on modern 3...
Emilien Seiler, Nicolas Talabot, Ying-Xuan You et al.
· 1 citation