[
    {
        "id": "osp-17876",
        "type": "article-journal",
        "title": "OverLay++: Dense-Overlap Layout-to-Image Generation Dataset",
        "author": [
            {
                "family": "Aggarwal",
                "given": "Shivansh"
            },
            {
                "family": "Grover",
                "given": "Shresth"
            },
            {
                "family": "Srivastava",
                "given": "Divyansh"
            },
            {
                "family": "Xu",
                "given": "Haiyang"
            },
            {
                "family": "Li",
                "given": "Bingnan"
            },
            {
                "family": "Zhang",
                "given": "Xiang"
            },
            {
                "family": "Armand",
                "given": "Ethan J."
            },
            {
                "family": "Li",
                "given": "Chuan"
            },
            {
                "family": "Xie",
                "given": "Jianwen"
            },
            {
                "family": "Tu",
                "given": "Zhuowen"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]