LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929520948281344 |
|---|---|
| author | Yu, Ning Chen, Chia-Chih Chen, Zeyuan Meng, Rui Wu, Gang Josel, Paul Niebles, Juan Carlos Xiong, Caiming Xu, Ran |
| author_facet | Yu, Ning Chen, Chia-Chih Chen, Zeyuan Meng, Rui Wu, Gang Josel, Paul Niebles, Juan Carlos Xiong, Caiming Xu, Ran |
| contents | Graphic layout designs play an essential role in visual communication. Yet handcrafting layout designs is skill-demanding, time-consuming, and non-scalable to batch production. Generative models emerge to make design automation scalable but it remains non-trivial to produce designs that comply with designers' multimodal desires, i.e., constrained by background images and driven by foreground content. We propose LayoutDETR that inherits the high quality and realism from generative modeling, while reformulating content-aware requirements as a detection problem: we learn to detect in a background image the reasonable locations, scales, and spatial relations for multimodal foreground elements in a layout. Our solution sets a new state-of-the-art performance for layout generation on public benchmarks and on our newly-curated ad banner dataset. We integrate our solution into a graphical system that facilitates user studies, and show that users prefer our designs over baselines by significant margins. Code, models, dataset, and demos are available at https://github.com/salesforce/LayoutDETR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_09877 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer Yu, Ning Chen, Chia-Chih Chen, Zeyuan Meng, Rui Wu, Gang Josel, Paul Niebles, Juan Carlos Xiong, Caiming Xu, Ran Computer Vision and Pattern Recognition Graphic layout designs play an essential role in visual communication. Yet handcrafting layout designs is skill-demanding, time-consuming, and non-scalable to batch production. Generative models emerge to make design automation scalable but it remains non-trivial to produce designs that comply with designers' multimodal desires, i.e., constrained by background images and driven by foreground content. We propose LayoutDETR that inherits the high quality and realism from generative modeling, while reformulating content-aware requirements as a detection problem: we learn to detect in a background image the reasonable locations, scales, and spatial relations for multimodal foreground elements in a layout. Our solution sets a new state-of-the-art performance for layout generation on public benchmarks and on our newly-curated ad banner dataset. We integrate our solution into a graphical system that facilitates user studies, and show that users prefer our designs over baselines by significant margins. Code, models, dataset, and demos are available at https://github.com/salesforce/LayoutDETR. |
| title | LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2212.09877 |