Research map / Image generation / Autoregressive and latent generation
PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
Chin-Yi Cheng, Forrest Huang, Gang Li, Yang Li
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 latent diffusion with a VAE first stage and guideline conditioning rather than VTN | PLay · CLAY | FID: 19.10 -> 10.59 | Improved |
| use latent diffusion with a VAE first stage and guideline conditioning rather than VTN | PLay · RICO-Semantic | FD-VG: 0.415 -> 0.320 | Improved |
| use latent diffusion with a VAE first stage and guideline conditioning rather than VTN | PLay · PublayNet | FD-VG: 0.787 -> 0.408 | Improved |
| add classifier-free guidance at weight 1.50 (ablation) | PLay with VAE first stage · CLAY | FID: 14.80 -> 10.59 | Improved |
| add a VAE first-stage latent representation (ablation) | PLay · CLAY | FID: 166.7 -> 10.59 | Improved |
| replace VAE with VQVAE as the first stage (ablation) | PLay · CLAY | G-Usage: 0.964 -> 0.937 | Hurt |
| use CFG weight 1.75 instead of 1.50 (ablation) | PLay · CLAY | FID: 10.59 -> 11.21 | Hurt |
| sample guideline subsets by overlap weight rather than uniformly (ablation) | PLay · CLAY | FID: 11.89 -> 10.59 | Improved |
| train with all guidelines instead of sampled subsets (ablation) | PLay · CLAY | FD-VG: 0.245 -> 0.206 | Improved |
| train with all guidelines instead of sampled subsets (ablation) | PLay · CLAY | G-Usage: 0.964 -> 0.917 | Hurt |
Later papers that compared with this method
1 later accepted paper reports PLay as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Dolfin: Diffusion Layout Transformers without Autoencoder (ECCV 2024 · better on 1 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.91)
- Unifying Layout Generation With a Decoupled Diffusion Model (CVPR 2023 · similarity 0.91)
- Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation (CVPR 2024 · similarity 0.89)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.88)
- MaskPLAN: Masked Generative Layout Planning from Partial Input (CVPR 2024 · similarity 0.87)
- DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models (CVPR 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.
