摘要：布局到图像生成在空间控制和物体级控制方面已取得显著进展。然而，现有方法在处理包含大量相互重叠、彼此交互物体的复杂场景时，仍然面临困难。我们认为，训练数据是一个特别关键的瓶颈：现有数据集缺少具有高密度、复杂物体交互的样本。为弥补这一空白，我们推出 OverLay++，这是一个包含结构复杂场景的大规模布局到图像数据集。OverLay++ 包含约 50 万张图像，平均每张图像含有 6.6 个物体，其标注密度是现有数据集的 1.67 倍。除标注密度外，OverLay++ 还提供丰富的语义细节，其物体描述的长度超过当前数据集的 6 倍。我们的数据集生成流程简单，能够产生具有丰富逐物体描述的密集重叠物体标注。在多个基准测试中，使用 OverLay++ 数据集训练的先进 Layout-to-Image 方法均表现出持续改进和更快的收敛速度，证明了高密度、重叠感知及描述丰富的监督数据对于可控图像生成的重要性。

Abstract:Layout-to-Image generation has made substantial progress in spatial and object-level control. However, existing methods still struggle with complex scenes containing many overlapping and interacting objects. We argue that training data is a particular bottleneck: existing datasets lack examples with dense, complex object interactions. To address this gap, we introduce OverLay++, a large-scale Layout-to-Image dataset with structurally complex scenes. OverLay++ contains approximately 500K images with an average of 6.6 objects per image, exceeding existing datasets by 1.67 times in annotation density. Beyond annotation density, OverLay++ provides rich semantic detail with object captions over six times longer than in current datasets. Our dataset generation pipeline is simple and produces dense, overlapping object annotations with rich per-object captions. Across multiple benchmarks, state-of-the-art Layout-to-Image methods trained on the OverLay++ dataset show consistent improvement and faster convergence, demonstrating the importance of dense, overlap-aware, and caption-rich supervision for controllable image generation.