WorldEdit: 向开放世界图像编辑迈进的基于知识的基准
WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
AI总结：
WorldEdit通过引入基于知识的基准，提升模型在开放世界图像编辑中对隐式指令的理解和处理能力。
摘要：
近期图像编辑模型的进步展示了在执行显式指令方面的显著能力，例如属性操控、风格迁移和姿态合成。然而，这些模型在处理隐式编辑指令时往往面临挑战，隐式指令描述了视觉变化的原因，但并未明确详细说明结果。这些限制源于现有模型依赖于统一的编辑策略，而无法处理隐式指令所需的复杂世界知识和推理。为了解决这一差距，我们引入WorldEdit，一个专门设计用于实现世界驱动图像编辑的数据集。WorldEdit包含高质量的编辑样本，由改写后的指令引导，这些指令与现实世界的因果逻辑一致。此外，我们还提供了WorldEdit-Test，用于评估现有模型在因果编辑场景中的性能。通过WorldEdit，我们使用两阶段训练框架对Bagel等模型进行微调，整合因果验证奖励。我们的结果表明，所提出的数据集和方法显著缩小了与GPT-4o和Nano-Banana之间的差距，展示了在指令遵循和知识合理性方面的竞争性性能，而许多开源系统通常在这些方面挣扎。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
