面向复杂图像编辑的鲁棒顺序分解
Towards Robust Sequential Decomposition for Complex Image Editing
AI总结：
提出通过顺序分解将复杂编辑任务拆解为简单步骤，并利用合成数据训练模型，在统一上下文编辑框架下平衡分解优势与误差累积，实现鲁棒改进和从模拟到真实的泛化。
摘要：
视觉生成模型的最新进展使得由人类指令引导的高保真图像编辑成为可能。然而，这些模型在处理涉及组合编辑操作或跨步骤依赖的复杂指令时常常遇到困难。这种困难源于两种典型范式的局限性：（1）单轮编辑，试图一次性应用所有指示的编辑，通常无法准确解析复杂指令并导致不期望的编辑；（2）顺序编辑可以将任务分解为更简单的步骤，但受到顺序执行引入的复合误差的影响，导致低保真结果。为了获得复杂图像编辑的鲁棒解决方案，我们在统一的上下文编辑框架下检查了不同范式的编辑行为，并研究了如何平衡顺序分解的优势与其误差累积的缺点。我们进一步开发了一个合成数据流水线，构建了不同指令复杂度的编辑任务，使我们能够整理一个具有高质量分解序列的大规模编辑数据集。通过在合成数据上进行微调，我们发现，通过适当设计的编辑范式，即使任务复杂度增加，顺序分解也能产生鲁棒的改进。此外，从合成任务中学到的分解技能可以通过与真实世界编辑数据共同训练迁移到真实图像，展示了模拟到真实泛化在更广泛领域中处理复杂图像编辑的前景。
英文摘要：
Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step dependencies. This difficulty stems from the limitations of two canonical paradigms: (1) single-turn editing, which attempts to apply all instructed edits in one pass, often fails to parse the complex instruction accurately and causes undesired edits; and (2) sequential editing can decompose the task into simpler steps but suffers from compounding errors introduced by the sequential execution, leading to low-fidelity results. To derive a robust solution for complex image editing, we examine editing behaviors of different paradigms under a unified in-context editing framework, and study how the benefits of sequential decomposition can be balanced against its error-accumulation drawbacks. We further develop a synthetic data pipeline that constructs editing tasks of varying instruction complexity, allowing us to curate a large-scale editing dataset with high-quality decomposed sequences. By finetuning on synthetic data, we discovered that with properly designed editing paradigms, sequential decomposition yields robust improvements even as task complexity increases. Furthermore, the decomposition skills learned from synthetic tasks can transfer to real images by co-training with real-world editing data, demonstrating the promise of sim-to-real generalization for tackling complex image editing across broader domains.
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。
