Research map / Image generation / Autoregressive and latent generation
LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction
Zhaoyun Jiang, Jiaqi Guo, Shizhao Sun, Huayu Deng, Zhongkai Wu, Vuksan Mijovic, Zijiang James Yang, Jian-Guang Lou, Dongmei Zhang
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 LayoutFormer++ instead of the strongest listed baseline | Gen-T layout generation · RICO | mIoU: 0.35 -> 0.432 | Improved |
| Use LayoutFormer++ instead of the strongest listed baseline | Gen-T layout generation · PubLayNet | mIoU: 0.31 -> 0.348 | Improved |
| Use LayoutFormer++ instead of BLT | Gen-TS layout generation · RICO | mIoU: 0.604 -> 0.620 | Improved |
| Use LayoutFormer++ instead of BLT | Gen-TS layout generation · PubLayNet | mIoU: 0.428 -> 0.471 | Improved |
| Use LayoutFormer++ instead of the strongest listed baseline | Gen-R layout generation · RICO | mIoU: 0.36 -> 0.424 | Improved |
| Use LayoutFormer++ instead of the strongest listed baseline | Gen-R layout generation · PubLayNet | mIoU: 0.31 -> 0.353 | Improved |
| Use LayoutFormer++ instead of RUITE | Refinement · RICO | mIoU: 0.811 -> 0.816 | Improved |
| Use LayoutFormer++ instead of RUITE | Refinement · PubLayNet | mIoU: 0.781 -> 0.785 | Improved |
| Use LayoutFormer++ instead of LayoutTransformer | Completion · RICO | mIoU: 0.363 -> 0.732 | Improved |
| Use LayoutFormer++ instead of LayoutTransformer | Completion · PubLayNet | mIoU: 0.077 -> 0.471 | Improved |
| Use LayoutFormer++ instead of VTN | UGen · RICO | mIoU: 0.686 -> 0.742 | Improved |
| Use LayoutFormer++ instead of Coarse2Fine | UGen · PubLayNet | mIoU: 0.361 -> 0.417 | Improved |
Later papers that compared with this method
2 later accepted papers report LayoutFormer++ as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- LayoutFlow: Flow Matching for Layout Generation (ECCV 2024 · better on 1 of 1 shared result)
- LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models (ICCV 2023 · better on 5 of 6 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
- LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models (ICLR 2024 · similarity 0.87)
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.87)
- OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps (NeurIPS 2025 · similarity 0.86)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.85)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.85)
- Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation (CVPR 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.
