Research map / Image generation / Autoregressive and latent generation
Coarse-to-Fine Generative Modeling for Graphic Layouts
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| generate layouts through region prediction followed by element placement | VAE layout generation · RICO | Align.: 0.373 -> 0.276 | Helped |
| generate layouts through region prediction followed by element placement | VAE layout generation · PubLayNet | Overlap: 0.017 -> 0.005 | Helped |
| generate layouts through region prediction followed by element placement | VAE layout generation · RICO | FID: 104.67 ± 29.51 -> 61.87 ± 5.77 | Helped |
| use positions relative to the region rather than absolute element positions (ablation) | coarse-to-fine layout generator · RICO | Align.: 0.470 -> 0.276 | Helped |
| use positions relative to the region rather than absolute element positions (ablation) | coarse-to-fine layout generator · RICO | CD: 0.041 -> 0.028 | Helped |
| use Android view hierarchy as the region segmentation instead of grid-line segmentation (ablation) | coarse-to-fine layout generator · RICO | Align.: 0.276 -> 0.320 | Hurt |
| use Android view hierarchy as the region segmentation instead of grid-line segmentation (ablation) | coarse-to-fine layout generator · RICO | Overlap: 0.139 -> 0.142 | Hurt |
| add a two-stage encoder for regions (ablation) | coarse-to-fine layout generator · RICO | CD: 0.028 -> 0.265 | Hurt |
| add a two-stage encoder for regions (ablation) | coarse-to-fine layout generator · RICO | Align.: 0.276 -> 0.522 | Hurt |
Closest papers by meaning
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.89)
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.88)
- LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models (ICLR 2024 · similarity 0.87)
- Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation (CVPR 2024 · similarity 0.87)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement (CVPR 2026 · similarity 0.87)
- Graphic Design with Large Multimodal Model (AAAI 2025 · similarity 0.87)
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.