Abstract
Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synthesis. However, these models often face challenges when dealing with implicit editing instructions, which describe the cause of a visual change without explicitly detailing the resulting outcome. These limitations arise because existing models rely on uniform editing strategies that are not equipped to handle the complex world knowledge and reasoning required for implicit instructions. To address this gap, we introduce \textbf{WorldEdit}, a dataset specifically designed to enable world-driven image editing. WorldEdit consists of high-quality editing samples, guided by paraphrased instructions that align with real-world causal logic. Furthermore, we provide \textbf{WorldEdit-Test} for evaluating the existing model's performance on causal editing scenarios. With WorldEdit, we use a two-stage training framework for fine-tuning models like Bagel, integrating with a causal verification reward. Our results show that the proposed dataset and methods significantly narrow the gap with GPT-4o and Nano-Banana, demonstrating competitive performance not only in instruction following but also in knowledge plausibility, where many open-source systems typically struggle.
Abstract (translated)
最近在图像编辑模型方面取得的进展展示了执行显式指令（如属性操控、风格转换和姿态合成）的非凡能力。然而，当面对隐含编辑指令时，这些模型往往会遇到挑战。隐含编辑指令描述的是视觉变化的原因而非详细的结果。现有模型面临的限制在于它们依赖于统一的编辑策略，无法处理实现隐含指令所需的复杂世界知识和推理过程。 为了解决这一差距，我们引入了\textbf{WorldEdit}，这是一个专门设计用于支持以世界驱动方式进行图像编辑的数据集。WorldEdit包括了大量的高质量编辑样本，并通过与现实世界的因果逻辑一致的语句指导这些样本的生成。此外，为了评估现有模型在处理因果编辑场景中的表现，我们还提供了名为\textbf{WorldEdit-Test}的测试数据集。 使用WorldEdit，我们提出了一种两阶段训练框架来对Bagel等模型进行微调，并结合了因果验证奖励机制。我们的实验结果表明，通过所提出的这一新数据集和方法，在遵循指令和知识合理性方面（这通常困扰着许多开源系统），与GPT-4o和Nano-Banana相比，差距显著缩小，展示了相当的性能水平。 这段翻译概述了一种新的图像编辑模型训练方式，并强调了它在处理因果性较强的隐含编辑任务时所取得的进步。
URL
https://arxiv.org/abs/2602.07095
