Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917284848599040 |
|---|---|
| author | Long, Zeqian Zheng, Mingzhe Feng, Kunyu Zhang, Xinhua Liu, Hongyu Yang, Harry Zhang, Linfeng Chen, Qifeng Ma, Yue |
| author_facet | Long, Zeqian Zheng, Mingzhe Feng, Kunyu Zhang, Xinhua Liu, Hongyu Yang, Harry Zhang, Linfeng Chen, Qifeng Ma, Yue |
| contents | While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08134 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control Long, Zeqian Zheng, Mingzhe Feng, Kunyu Zhang, Xinhua Liu, Hongyu Yang, Harry Zhang, Linfeng Chen, Qifeng Ma, Yue Computer Vision and Pattern Recognition While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement. |
| title | Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.08134 |