WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
This addresses a bottleneck in open-world image editing for AI systems, though it is incremental as it builds on existing models like Bagel.
The paper tackles the problem of image editing models struggling with implicit instructions that require world knowledge and reasoning, by introducing the WorldEdit dataset and a two-stage training framework, resulting in competitive performance with GPT-4o and Nano-Banana in knowledge plausibility.
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.