GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images

2026-07-01

AI Summary

This work addresses the challenges of precise execution in e-commerce image editing, where multiple operations, localized modifications, and auditability requirements often lead to partial failures in existing methods due to the tight coupling of intent understanding, region localization, and image generation. To overcome this, we propose a decoupled cognitive-generation agent framework that leverages a vision-language model to construct region-anchored editing agendas, guides a diffusion-based editor with operation-aware masks for stepwise execution, and incorporates a reflection-driven iterative mechanism to ensure editing completeness and error correctability. Our approach achieves the first structured decoupling of cognitive reasoning and generative rendering, significantly outperforming open-source alternatives on our newly curated benchmark, EComEditBench, while matching the instruction accuracy and editing fidelity of powerful closed-source models and enabling traceable, recoverable multi-turn editing workflows.

Abstract

Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling. This compositional nature poses a dual challenge: models must precisely apply all requested edits to the correct regions while preserving unmodified content, even under ambiguous instructions. Existing one-shot editors conflate intent resolution, spatial grounding, and synthesis into a single step, frequently resulting in partial execution failures, which is unacceptable for commercial scenarios. To address this, we introduce GMO-E$^2$DIT, an agentic editing framework that couples a Vision-Language Model (VLM) with a mask-conditioned image editor to tackle structured multi-turn task completion. Given an underspecified instruction, the VLM agent constructs a region-grounded edit agenda, effectively decoupling cognitive reasoning from generative rendering. The framework then executes sub-programs via operation-aware masks and references, utilizing a reflection-driven loop to inspect intermediate results and determine the subsequent state. This iterative mechanism reliably preserves safe partial progress, retries unfinished operations, and recovers from errors. Furthermore, we develop a unified data pipeline providing aligned supervision for planning, execution, and reflection, alongside EComEditBench, a comprehensive benchmark for instruction-driven evaluation. Extensive experiments demonstrate that GMO-E$^2$DIT achieves competitive performance compared to strong closed-source models, yielding superior instruction accuracy and edit fidelity over existing baselines.

Problem

• e-commerce image editing
• multi-operation editing
• spatial grounding
• instruction ambiguity
• edit fidelity

Innovation

• agentic editing
• region-grounded editing
• mask-conditioned generation
• reflection-driven loop
• multi-operation image editing