Research map / Image generation / Text-to-image diffusion
Freestyle Layout-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 |
|---|---|---|---|
| Use layout-rectified cross-attention with a pre-trained diffusion model instead of conventional LIS models | FreestyleNet · COCO-Stuff | FID: 16.1 -> 14.4 | Helped |
| Use layout-rectified cross-attention with a pre-trained diffusion model instead of conventional LIS models | FreestyleNet · ADE20K | FID: 27.9 -> 25.0 | Helped |
| Use FreestyleNet instead of PITI for spatial alignment | COCO-Stuff · COCO-Stuff | mIoU: 13.1 -> 40.7 | Helped |
| Use FreestyleNet instead of PITI for spatial alignment | ADE20K · ADE20K | mIoU: 41.9 vs 48.8 | Mixed |
| Use FreestyleNet rather than PITI for generation diversity | FreestyleNet · COCO-Stuff | LPIPS: 0.523 -> 0.592 | Helped |
| Use FreestyleNet rather than PITI for generation diversity | FreestyleNet · ADE20K | LPIPS: 0.480 -> 0.591 | Helped |
| Use stacked semantic concepts rather than keyword-to-sentence translation (ablation) | FreestyleNet text inputs · layout-to-image synthesis | generation performance | Helped |
| Use stacked semantic concepts rather than learnable prompts (ablation) | FreestyleNet text inputs · layout-to-image synthesis | generation performance | Helped |
| Use stacked semantic concepts rather than manually constructed full-form prompts (ablation) | FreestyleNet text inputs · layout-to-image synthesis | generation performance | Helped |
Closest papers by meaning
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.88)
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.88)
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 2024 · similarity 0.88)
- Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive (ICLR 2024 · similarity 0.87)
- SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation (AAAI 2024 · similarity 0.87)
- Grounded Text-to-Image Synthesis with Attention Refocusing (CVPR 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.