Research map / Image generation / Text-to-image diffusion
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
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 |
|---|---|---|---|
| infer semantic layouts and condition image synthesis on them | Text-to-image synthesis · MS-COCO 2014 validation | CIDEr: 0.195 -> 0.367 | Helped |
| infer semantic layouts and condition image synthesis on them | Text-to-image synthesis · MS-COCO 2014 validation | Inception score: 8.45 ± 0.03 -> 11.46 ± 0.09 | Helped |
| replace predicted boxes with ground-truth boxes (ablation) | Text-to-image synthesis with inferred layouts · MS-COCO 2014 validation | CIDEr: 0.367 -> 0.400 | Helped |
| replace predicted boxes and masks with ground-truth boxes and masks (ablation) | Text-to-image synthesis with inferred layouts · MS-COCO 2014 validation | CIDEr: 0.367 -> 0.440 | Helped |
| add the shape generator (ablation) | Text-to-image synthesis · MS-COCO 2014 validation | CIDEr: 0.215 -> 0.367 | Helped |
| use perceptual loss instead of pixelwise L1 loss in the shape generator (ablation) | Text-to-image synthesis · MS-COCO 2014 validation | CIDEr: 0.324 -> 0.367 | Helped |
| use perceptual loss instead of pixelwise L1 loss in the image generator (ablation) | Text-to-image synthesis · MS-COCO 2014 validation | CIDEr: 0.170 -> 0.367 | Helped |
| add attention to the image generator (ablation) | Text-to-image synthesis · MS-COCO 2014 validation | CIDEr: 0.324 -> 0.367 | Helped |
Closest papers by meaning
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 2024 · similarity 0.90)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.90)
- HDLayout: Hierarchical and Directional Layout Planning for Arbitrary Shaped Visual Text Generation (AAAI 2025 · similarity 0.89)
- SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation (AAAI 2024 · similarity 0.88)
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts (ICLR 2024 · similarity 0.88)
- Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis (NeurIPS 2024 · 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.