OverLayBench：面向密集重叠布局到图像生成的基准测试

摘要

尽管在布局到图像生成领域取得了稳步进展，现有方法在处理包含显著边界框重叠的布局时仍面临困难。我们识别出两大主要挑战：（1）大面积的重叠区域，以及（2）语义区分度极低的重叠实例。通过定性示例与定量分析，我们展示了这些因素如何降低生成质量。为了系统性地评估这一问题，我们引入了OverLayScore，一种新颖的指标，用于量化重叠边界框的复杂性。我们的分析揭示，现有基准测试偏向于OverLayScore值较低的简单案例，限制了其在更具挑战性条件下评估模型性能的有效性。为填补这一空白，我们提出了OverLayBench，一个包含高质量标注且在不同OverLayScore水平间均衡分布的新基准。作为提升复杂重叠场景下性能的初步尝试，我们还提出了CreatiLayout-AM模型，该模型在精选的无模态掩码数据集上进行了微调。综合而言，我们的贡献为在现实且具挑战性的场景下实现更稳健的布局到图像生成奠定了基础。项目链接：https://mlpc-ucsd.github.io/OverLayBench。

English

Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary challenges: (1) large overlapping regions and (2) overlapping instances with minimal semantic distinction. Through both qualitative examples and quantitative analysis, we demonstrate how these factors degrade generation quality. To systematically assess this issue, we introduce OverLayScore, a novel metric that quantifies the complexity of overlapping bounding boxes. Our analysis reveals that existing benchmarks are biased toward simpler cases with low OverLayScore values, limiting their effectiveness in evaluating model performance under more challenging conditions. To bridge this gap, we present OverLayBench, a new benchmark featuring high-quality annotations and a balanced distribution across different levels of OverLayScore. As an initial step toward improving performance on complex overlaps, we also propose CreatiLayout-AM, a model fine-tuned on a curated amodal mask dataset. Together, our contributions lay the groundwork for more robust layout-to-image generation under realistic and challenging scenarios. Project link: https://mlpc-ucsd.github.io/OverLayBench.

OverLayBench：面向密集重叠布局到图像生成的基准测试

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps

摘要

Support