ComplexBench-Edit：通过组合依赖关系对复杂指令驱动的图像编辑进行基准测试
ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies
AI总结：
针对现有图像编辑模型难处理复杂多步链式指令、基准评估不足的问题，提出ComplexBench-Edit基准及新视觉一致性评估方法，还设计了基于CoT的方法提升模型复杂指令遵循能力，实验验证了二者的有效性。
摘要：
文本驱动的图像编辑在遵循单条指令方面已取得显著成效。然而，现实场景中往往涉及复杂的多步骤指令，尤其是操作相互依赖的“链式”指令。当前模型难以应对这类复杂指令，且现有基准测试对这类能力的评估存在不足。具体而言，它们通常忽略了多指令和链式指令的复杂性，且常用的一致性指标存在缺陷。为解决这一问题，我们提出了ComplexBench-Edit，这是一款新型基准测试工具，旨在系统评估模型在复杂、多指令及链式依赖图像编辑任务上的性能。ComplexBench-Edit还具备一种全新的视觉一致性评估方法，可通过排除编辑区域来准确评估未修改区域。此外，我们提出了一种简单却强大的基于思维链（Chain-of-Thought, CoT）的方法，显著提升了现有模型遵循复杂指令的能力。我们开展的大量实验证明了ComplexBench-Edit在区分模型能力方面的有效性，也凸显了我们基于CoT的方法在处理复杂编辑任务上的优越性能。相关数据和代码已发布于https://github.com/llllly26/ComplexBench-Edit。
英文摘要：
Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ``chain'' instructions where operations are interdependent. Current models struggle with these intricate directives, and existing benchmarks inadequately evaluate such capabilities. Specifically, they often overlook multi-instruction and chain-instruction complexities, and common consistency metrics are flawed. To address this, we introduce ComplexBench-Edit, a novel benchmark designed to systematically assess model performance on complex, multi-instruction, and chain-dependent image editing tasks. ComplexBench-Edit also features a new vision consistency evaluation method that accurately assesses non-modified regions by excluding edited areas. Furthermore, we propose a simple yet powerful Chain-of-Thought (CoT)-based approach that significantly enhances the ability of existing models to follow complex instructions. Our extensive experiments demonstrate ComplexBench-Edit's efficacy in differentiating model capabilities and highlight the superior performance of our CoT-based method in handling complex edits. The data and code are released at https://github.com/llllly26/ComplexBench-Edit.
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。
