Research map / Image generation / Text-to-image diffusion
Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion
Shengqiong Wu, Hao Fei, Hanwang Zhang, Tat-Seng Chua
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 |
|---|---|---|---|
| remove whole scene graph hallucination (SGH) module (ablation) | Salad · COCO | FID: 10.19 -> 16.98 | Hurt |
| remove whole SGH module (ablation) | Salad · COCO-A2I | FID: 31.25 -> 34.32 | Hurt |
| use initial text SG instead of SG enrichment (ablation) | Salad · COCO | FID: 10.19 -> 12.45 | Hurt |
| use initial text SG instead of SG enrichment (ablation) | Salad · COCO-A2I | FID: 31.25 -> 37.77 | Hurt |
| remove Graph-CA (Eq.4) (ablation) | Salad · COCO | FID: 10.19 -> 10.95 | Hurt |
| remove Graph-CA (Eq.4) (ablation) | Salad · COCO-A2I | FID: 31.25 -> 32.74 | Hurt |
| remove node-type dependence cross-attention (NTD-CA) (ablation) | Salad · COCO-A2I | FID: 31.25 -> 34.35 | Hurt |
| remove node-type dependence cross-attention (NTD-CA) (ablation) | Salad · COCO | FID: 10.19 -> 11.19 | Hurt |
| replace hierarchical SG integration with a GCN encoder (ablation) | Salad · COCO-A2I | FID: 31.25 -> 35.96 | Hurt |
| replace hierarchical SG integration with a GCN encoder (ablation) | Salad · COCO | FID: 10.19 -> 10.87 | Hurt |
| text-based enrichment (SPY) added to Frido instead of SGH | Frido · COCO-A2I | CLIP score: 68.53 -> 67.86 | No clear effect |
| text-based enrichment (SPY) added to Frido | Frido · COCO-A2I | FID: 40.36 -> 35.59 | Improved |
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.
- DFGAN — DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR 2022) · better on 1 of 1 shared result
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
- Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.89)
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.88)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.88)
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts (ICLR 2024 · similarity 0.88)
- VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis (AAAI 2025 · similarity 0.88)
- SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation (AAAI 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.
