Research map / Image generation / GANs
LayoutGAN: Synthesizing Graphic Layouts With Vector-Wireframe Adversarial Networks
Jianan Li, Jimei Yang, Aaron Hertzmann, Jianming Zhang, Tingfa Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use wireframe rendering discriminator instead of relation-based discriminator (ablation) | LayoutGAN · MNIST digit generation | inception score: 6.53 -> 7.36 | Improved |
| use wireframe rendering discriminator instead of relation-based discriminator (ablation) | LayoutGAN · Document layout generation | overlap index (%): 1.52 -> 1.17 | Improved |
| use wireframe rendering discriminator instead of relation-based discriminator (ablation) | LayoutGAN · Document layout generation | alignment index (%): 6.4 -> 3.4 | Improved |
| use wireframe rendering discriminator instead of relation-based discriminator (ablation) | LayoutGAN · Clipart abstract scenes user study | rated excellent (%): 17.2 -> 37.3 | Improved |
| use wireframe rendering discriminator instead of relation-based discriminator (ablation) | LayoutGAN · Clipart abstract scenes user study | rated poor (%): 32.5 -> 14.7 | Improved |
| use LayoutGAN relation-based discriminator instead of DCGAN pixel mask generation (ablation) | LayoutGAN · Clipart abstract scenes user study | rated excellent (%): 6.7 -> 17.2 | Improved |
| use LayoutGAN relation-based discriminator instead of DCGAN pixel mask generation (ablation) | LayoutGAN · Clipart abstract scenes user study | rated poor (%): 54.5 -> 32.5 | Improved |
Closest papers by meaning
- LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators (ICLR 2019 · similarity 0.99)
- Neural Design Network: Graphic Layout Generation with Constraints (ECCV 2020 · similarity 0.89)
- Interactive Image Synthesis With Panoptic Layout Generation (CVPR 2022 · similarity 0.89)
- Image Synthesis From Reconfigurable Layout and Style (ICCV 2019 · similarity 0.89)
- StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN (CVPR 2024 · similarity 0.85)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
