Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914572372279296 |
|---|---|
| author | Xu, Shaodong Li, Zexian Wang, Zhendong Gong, Litong Ge, Tiezheng Zhou, Wengang Zheng, Bo Li, Houqiang |
| author_facet | Xu, Shaodong Li, Zexian Wang, Zhendong Gong, Litong Ge, Tiezheng Zhou, Wengang Zheng, Bo Li, Houqiang |
| contents | A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, most optimization-based editing approaches treat images as holistic entities, causing global policy updates that undermine locality and introduce undesired context changes. We observe that this issue stems from a mismatch between localized editing intent and globally applied optimization signals. Motivated by this insight, we propose Edit-GRPO, preserving Locality while optimizing image editing, a locality-preserving policy optimization framework that explicitly decouples editing and preservation objectives. By assigning region-specific optimization signals to edit and non-edit areas, Edit-GRPO aligns policy updates with the spatial structure of editing tasks, enabling localized improvements while maintaining global visual coherence. This design effectively suppresses common artifacts such as context distortion and boundary inconsistency. Extensive experiments across diverse image editing scenarios demonstrate that Edit-GRPO significantly improves locality preservation while maintaining strong editing performance compared to existing optimization-based methods, validating the generality and effectiveness of the proposed framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16951 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing Xu, Shaodong Li, Zexian Wang, Zhendong Gong, Litong Ge, Tiezheng Zhou, Wengang Zheng, Bo Li, Houqiang Computer Vision and Pattern Recognition A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, most optimization-based editing approaches treat images as holistic entities, causing global policy updates that undermine locality and introduce undesired context changes. We observe that this issue stems from a mismatch between localized editing intent and globally applied optimization signals. Motivated by this insight, we propose Edit-GRPO, preserving Locality while optimizing image editing, a locality-preserving policy optimization framework that explicitly decouples editing and preservation objectives. By assigning region-specific optimization signals to edit and non-edit areas, Edit-GRPO aligns policy updates with the spatial structure of editing tasks, enabling localized improvements while maintaining global visual coherence. This design effectively suppresses common artifacts such as context distortion and boundary inconsistency. Extensive experiments across diverse image editing scenarios demonstrate that Edit-GRPO significantly improves locality preservation while maintaining strong editing performance compared to existing optimization-based methods, validating the generality and effectiveness of the proposed framework. |
| title | Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.16951 |