Research map / Image generation / Autoregressive and latent generation
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Ning Yu, Chia-chih Chen, Zeyuan Chen, Rui Meng, Gang Wu, Paul W Josel, Juan Carlos Niebles, Caiming Xiong, Ran 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 |
|---|---|---|---|
| add auxiliary decoders to the discriminators (ablation) | Conditional LayoutGAN++ · Ad banner dataset | Layout FID: 11.33 -> 4.25 | Improved |
| add generator reconstructor of conditional inputs (ablation) | LayoutDETR-GAN · Ad banner dataset | Layout FID: 4.25 -> 3.27 | Improved |
| add unconditional discriminator (ablation) | LayoutDETR-GAN · Ad banner dataset | Misalignment (x10^-2): 0.853 -> 0.681 | Mixed |
| add gIoU loss (ablation) | LayoutDETR-GAN · Ad banner dataset | Layout KID (x10^-3): 16.23 -> 11.60 | Improved |
| add overlap and misalignment losses (ablation) | LayoutDETR-GAN · Ad banner dataset | Layout KID (x10^-3): 11.60 -> 5.62 | Improved |
| add text length embeddings (ablation) | LayoutDETR-GAN · Ad banner dataset | Misalignment (x10^-2): 0.807 -> 0.646 | Improved |
| add text class embeddings (ablation) | LayoutDETR-GAN · Ad banner dataset | Layout FID: 25.17 -> 3.24 | Improved |
| combine VAE with GAN (VAE-GAN) instead of GAN only | LayoutDETR · CGL Chinese ad banner dataset | Layout FID: 2.40 -> 2.65 | Mixed |
| use LayoutDETR-VAE-GAN instead of LayoutDETR-GAN | LayoutDETR · CLAY mobile UI dataset | Layout FID: 1.84 -> 3.98 | Hurt |
| use LayoutDETR-GAN instead of baselines in human preference | layout baselines · Ad banner user study | pairwise preference: 54.2% to 63.5% | Improved |
Closest papers by meaning
- CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation (ICCV 2025 · similarity 0.89)
- Graphic Design with Large Multimodal Model (AAAI 2025 · similarity 0.88)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.88)
- Desigen: A Pipeline for Controllable Design Template Generation (CVPR 2024 · similarity 0.87)
- Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation (CVPR 2024 · similarity 0.87)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.86)
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.
