OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916965005656064 |
|---|---|
| author | Li, Bingnan Wang, Chen-Yu Xu, Haiyang Zhang, Xiang Armand, Ethan Srivastava, Divyansh Shan, Xiaojun Chen, Zeyuan Xie, Jianwen Tu, Zhuowen |
| author_facet | Li, Bingnan Wang, Chen-Yu Xu, Haiyang Zhang, Xiang Armand, Ethan Srivastava, Divyansh Shan, Xiaojun Chen, Zeyuan Xie, Jianwen Tu, Zhuowen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19282 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps Li, Bingnan Wang, Chen-Yu Xu, Haiyang Zhang, Xiang Armand, Ethan Srivastava, Divyansh Shan, Xiaojun Chen, Zeyuan Xie, Jianwen Tu, Zhuowen Computer Vision and Pattern Recognition 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. |
| title | OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.19282 |