BROWSE
Detail
Conference Paper
V-HOLD: Stabilizing Flow Trajectories to Rethink the Edit–Preservation Trade-off
Cited - time in 
Share 
Share
- Authors
- Gahyeon Kim, Dong-oh Kang
- Issue Date
- 2026-09
- Citation
- European Conference on Computer Vision (ECCV) 2026, pp.1-16
- Publisher
- Springer
- Language
- English
- Type
- Conference Paper
- Abstract
- Recent diffusion- and flow-based image editing methods en-able high-quality text-guided image editing. However, improving editstrength often degrades identity and background preservation, a phe-nomenon known as the edit—preservation trade-off. This trade-off iswidely observed and commonly regarded as an inherent limitation ofgenerative editing. In this work, we revisit this assumption and iden-tify trajectory instability as a previously overlooked factor behind theedit–preservation trade-off. Through empirical analysis across multipleediting methods and backbones, we find that trajectory instability isclosely associated with degraded semantic preservation while showinglittle association with edit alignment. We characterize instability by us-ing directional consistency and update variability of latent update ve-locities during integration, revealing that unstable integration dynamicscontribute substantially to the edit–preservation trade-off. Motivated bythis insight, we propose V-HOLD, a simple training-free method thatstabilizes editing trajectories by maintaining a target-oriented updatedirection across multiple integration steps instead of recomputing veloc-ities at every step. Experiments on PIE-Bench and the FlowEdit-Datashow that our method consistently improves semantic preservation whilemaintaining competitive edit alignment across multiple backbones. Inaddition, V-HOLD reduces the number of velocity-field evaluations dur-ing editing, improving computational efficiency. These results highlighttrajectory stability as a key factor for improving semantic preservationwithout sacrificing edit alignment.
- Keyword
- Text-guided Image Editing, Generative Image Editing, Trajectory Stability
- KSP Keywords
- Computational Efficiency, Flow-based(FB), High-quality, Image editing, Key factor, Trade-off, empirical analysis, multiple integration, velocity-field