From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913130049699840 |
|---|---|
| author | Rajan, Anirudh Sundara Singh, Krishna Kumar Lee, Yong Jae |
| author_facet | Rajan, Anirudh Sundara Singh, Krishna Kumar Lee, Yong Jae |
| contents | Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15181 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing Rajan, Anirudh Sundara Singh, Krishna Kumar Lee, Yong Jae Computer Vision and Pattern Recognition Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines. |
| title | From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.15181 |