Research map / Image generation / Autoregressive and latent generation
Neural Design Network: Graphic Layout Generation with Constraints
Hsin-Ying Lee, Lu Jiang, Irfan Essa, Phuong B Le, Haifeng Gong, Ming-Hsuan Yang, Weilong Yang
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 |
|---|---|---|---|
| add refinement module (20% constraints) (ablation) | NDN · RICO | FID: 126.18 -> 125.41 | Improved |
| add refinement module (20% constraints) (ablation) | NDN · RICO | alignment: 0.74 -> 0.70 | Improved |
| add refinement module (100% constraints) (ablation) | NDN · RICO | FID: 70.55 -> 64.78 | Improved |
| add refinement module (100% constraints) (ablation) | NDN · RICO | alignment: 0.36 -> 0.32 | Improved |
| provide 20% location constraints instead of none (ablation) | NDN · RICO | FID: 143.51 -> 129.92 | Improved |
| provide 20% size constraints instead of none (ablation) | NDN · RICO | FID: 143.51 -> 141.64 | Improved |
| provide all constraints instead of none (ablation) | NDN · RICO | FID: 143.51 -> 64.78 | Improved |
| order components by size instead of random (ablation) | NDN · RICO | FID: 143.51 -> 132.84 | Improved |
| order components by occurrence instead of random (ablation) | NDN · RICO | FID: 143.51 -> 136.22 | Improved |
| order components by size instead of random (ablation) | NDN · RICO | prediction error: 0.91 -> 1.08 | Hurt |
| graph-based NDN-none instead of LayoutVAE (no constraint) | NDN · RICO | FID: 192.11 -> 143.51 | Improved |
| graph-based NDN-loo instead of LayoutVAE-loo | NDN · RICO | prediction error: 0.045 -> 0.018 | Improved |
Closest papers by meaning
- LayoutGAN: Synthesizing Graphic Layouts With Vector-Wireframe Adversarial Networks (TPAMI 2020 · similarity 0.89)
- Graphic Design with Large Multimodal Model (AAAI 2025 · similarity 0.86)
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.86)
- Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation (CVPR 2024 · similarity 0.85)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.85)
- Constrained Layout Generation with Factor Graphs (CVPR 2024 · similarity 0.84)
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.
