Research map / Image generation / Text-to-image diffusion
A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions
Jiawei Lin, Jiaqi Guo, Shizhao Sun, Weijiang Xu, Ting Liu, 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 |
|---|---|---|---|
| initialize parse stage with T5 pretrained weights instead of random (ablation) | parse stage · WebUI | IR accuracy: 35.5% -> 76.2% | Improved |
| initialize parse stage with T5 pretrained weights instead of random (ablation) | parse stage · RICO | IR accuracy: 9.9% -> 56.6% | Improved |
| pretrain place model on 1.5M unlabeled layouts (ablation) | place stage · WebUI | FID: 3.8141 -> 2.9592 | Improved |
| pretrain place model on 1.5M unlabeled layouts (ablation) | place stage · WebUI | mIoU: 0.5773 -> 0.6841 | Improved |
| pretrain with more unlabeled layouts on diversity (Unique Match) (ablation) | place stage · WebUI | Unique Match: 0.6304 -> 0.5080 | Hurt |
| use two-stage parse-then-place instead of end-to-end T5 (ablation) | parse-then-place · WebUI | mIoU: 0.3168 -> 0.5773 | Improved |
| feed golden IR to the place stage (ablation) | parse-then-place · WebUI | Type consistency: 0.8864 -> 0.9532 | Improved |
| parse-then-place versus SR-BERT, Text2Scene and Mockup | parse-then-place · WebUI | FID: 10.1640 -> 2.9592 | Improved |
| parse-then-place versus SR-BERT in user study | parse-then-place · RICO user study | preferred for perceptual quality: 0.205 -> 0.625 | Improved |
| layouts with more elements (ablation) | parse-then-place · WebUI | FID: 5.3173 -> 16.0709 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Text2Scene — Text2Scene: Generating Compositional Scenes From Textual Descriptions (CVPR 2019) · better on 2 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 0.88)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement (CVPR 2026 · similarity 0.88)
- HDLayout: Hierarchical and Directional Layout Planning for Arbitrary Shaped Visual Text Generation (AAAI 2025 · similarity 0.87)
- LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models (ICLR 2024 · similarity 0.87)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.86)
- 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.
