الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Aggarwal, S., Grover, S., Srivastava, D., Xu, H., Li, B., Zhang, X., Armand, E. J., Li, C., Xie, J., & Tu, Z. (2026). OverLay++: Dense-Overlap Layout-to-Image Generation Dataset. https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset
MLA 9
Aggarwal, Shivansh, et al. "OverLay++: Dense-Overlap Layout-to-Image Generation Dataset." https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset.
شيكاغو (المؤلف–التاريخ)
Aggarwal, Shivansh, Shresth Grover, Divyansh Srivastava, Haiyang Xu, Bingnan Li, Xiang Zhang, Ethan J. Armand, Chuan Li, Jianwen Xie, and Zhuowen Tu. 2026. "OverLay++: Dense-Overlap Layout-to-Image Generation Dataset." https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset.
هارفارد
Aggarwal, S., Grover, S., Srivastava, D., Xu, H., Li, B., Zhang, X., Armand, E. J., Li, C., Xie, J. and Tu, Z. (2026) 'OverLay++: Dense-Overlap Layout-to-Image Generation Dataset', Available at: https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset.
فانكوفر
Aggarwal S, Grover S, Srivastava D, Xu H, Li B, Zhang X, et al. OverLay++: Dense-Overlap Layout-to-Image Generation Dataset. https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset
IEEE
S. Aggarwal, S. Grover, D. Srivastava, H. Xu, B. Li, X. Zhang, E. J. Armand, C. Li, J. Xie, and Z. Tu, "OverLay++: Dense-Overlap Layout-to-Image Generation Dataset," https://omanscience.com/ar/articles/overlay-dense-overlap-layout-to-image-generation-dataset.