SpotEdit：评估视觉引导的图像编辑方法
SpotEdit: Evaluating Visually-Guided Image Editing Methods
AI总结：
本文提出 SpotEdit 基准，系统评估跨扩散、自回归与混合模型的视觉引导图像编辑能力，并专门考察视觉线索幻觉导致的错误编辑问题。
摘要：
视觉引导的图像编辑是指编辑同时以视觉线索和文本提示为条件，已成为用于细粒度、可控内容生成的强大范式。尽管近期的生成模型已展现出显著能力，但现有评估仍然简单，且不足以代表真实世界的编辑挑战。我们提出 SpotEdit，这是一个综合性基准，旨在系统评估视觉引导的图像编辑方法，涵盖多种扩散、自回归和混合生成模型，揭示了巨大的性能差距。为解决一个关键但探索不足的挑战，我们的基准包含一个专门针对幻觉的组成部分，强调了 GPT-4o 等领先模型如何经常幻觉出某个视觉线索的存在，并错误地执行编辑任务。我们的代码和基准已在 https://github.com/SaraGhazanfari/SpotEdit 公开发布。
英文摘要：
Visually-guided image editing, where edits are conditioned on both visual cues and textual prompts, has emerged as a powerful paradigm for fine-grained, controllable content generation. Although recent generative models have shown remarkable capabilities, existing evaluations remain simple and insufficiently representative of real-world editing challenges. We present SpotEdit, a comprehensive benchmark designed to systematically assess visually-guided image editing methods across diverse diffusion, autoregressive, and hybrid generative models, uncovering substantial performance disparities. To address a critical yet underexplored challenge, our benchmark includes a dedicated component on hallucination, highlighting how leading models, such as GPT-4o, often hallucinate the existence of a visual cue and erroneously perform the editing task. Our code and benchmark are publicly released at https://github.com/SaraGhazanfari/SpotEdit.
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。
