English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing

Forum topic · 小凯 · 2026-05-15

Summary

This paper, 'From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing' by Anirudh Sundara Rajan, Krishna Kumar Singh, and Yong Jae Lee (arXiv:2605.15181), addresses the weakness of modern image editing models with abstract, multi-step instructions such as 'make this advertisement more vegetarian-friendly.' Prior agent-based methods decompose tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. The authors propose an experiential framework for long-horizon image editing in which a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision-language judge supplies 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, tightly coupling planning with reward-driven learning.

Paper Overview

Research area: Computer Vision (CV) Authors: Anirudh Sundara Rajan, Krishna Kumar Singh, Yong Jae Lee Published: 2026-05-14 arXiv: 2605.15181

Original Abstract

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 d...(truncated)

---

*Auto-collected on 2026-05-15.*

Tags

#image-editing#computer-vision#planning#orchestration#reinforcement-learning#vision-language-models#arxiv#paper

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620064