基于布局引导的图像生成的诊断基准和迭代修复（英文版）

英文标题：Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation中文摘要：本文提出了 LayoutBench 和 IterInpaint 两个基于互补技术的图像布局与生成模型，旨在解决现有模型在处理任意或未见过的图像布局方面的不足，同时在四个空间控制技能方面进行定量和定性评估。英文摘要：Spatial control is a core capability in controllable image generation.Advancements in layout-guided image generation have shown promising results onin-distribution (ID) datasets with similar spatial configurations. However, itis unclear how these models perform when facing out-of-distribution (OOD)sam