Pith. sign in

REVIEW 5 cited by

FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.23145 v4 pith:Q6F5PTGB submitted 2025-05-29 cs.CV cs.AIcs.LG

Jeongsol Kim , Yeobin Hong , Jonghyun Park , Jong Chul Ye This is my paper
classification cs.CVcs.AIcs.LG
keywords editingflowalignimagesourceconsistentflow-basedinversion-freemethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent inversion-free, flow-based image editing methods such as FlowEdit leverages a pre-trained noise-to-image flow model such as Stable Diffusion 3, enabling text-driven manipulation by solving an ordinary differential equation (ODE). While the lack of exact latent inversion is a core advantage of these methods, it often results in unstable editing trajectories and poor source consistency. To address this limitation, we propose {\em FlowAlign}, a novel inversion-free flow-based framework for consistent image editing with optimal control-based trajectory control. Specifically, FlowAlign introduces source similarity at the terminal point as a regularization term to promote smoother and more consistent trajectories during the editing process. Notably, our terminal point regularization is shown to explicitly balance semantic alignment with the edit prompt and structural consistency with the source image along the trajectory. Furthermore, FlowAlign naturally supports reverse editing by simply reversing the ODE trajectory, highliting the reversible and consistent nature of the transformation. Extensive experiments demonstrate that FlowAlign outperforms existing methods in both source preservation and editing controllability.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform

    cs.CV 2026-07 conditional novelty 6.5 of 10

    h-Flow extends Doob's h-transform to deterministic rectified flows via an equivalent SDE, yielding closed-form reconstruction guidance plus orthogonal velocity editing for controllable text-based image editing.

  2. ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Test-time tuning of video diffusion models collapses generation toward the source video; ElasticTTT counters this with noisy targets, contrastive source-prompt guidance, and asynchronous region-wise noise scheduling, ...

  3. Bridging the Manifold Gap: Riemannian Residual Line Search for One-Step Image Editing

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Second-order curvature-corrected residual line search over energy-field transport candidates yields SOTA one-step text-guided image editing on PIE-Bench++.

  4. Translationese as a Rational Response to Translation Task Difficulty

    cs.CL 2026-03 unverdicted novelty 5.0 of 10

    Translationese is partly predictable from quantifiable translation-task difficulty, especially cross-lingual transfer load, more so for English-to-German than the reverse.

  5. FlowSteer: Conditioning Flow Field for Consistent Image Restoration

    eess.IV 2025-12 conditional novelty 5.0 of 10

    A sparse mid-to-late schedule of null-space fidelity updates lets a frozen text-to-image flow model restore images with high measurement consistency.

Pith tools