Research map / Vision-language and multimodal / Multimodal LLMs
Multimodal Image Synthesis and Editing: The Generative AI Era
Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Lingjie Liu, Adam Kortylewski, Christian Theobalt, Eric P. Xing
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 diffusion-based SDM instead of GAN-based OASIS | segmentation-to-image · Cityscapes | FID: 47.7 -> 42.1 | Improved |
| use SDM instead of OASIS | segmentation-to-image · COCO-Stuff | mIoU: 46.7 -> 40.2 | Hurt |
| use SDM instead of OASIS | segmentation-to-image · ADE20K | LPIPS diversity: 0.286 -> 0.524 | Improved |
| use large-scale diffusion (Imagen) instead of DALL-E | text-to-image · COCO | FID: 27.50 -> 7.270 | Improved |
| use autoregressive Parti instead of diffusion Imagen | text-to-image · COCO | FID: 7.270 -> 7.230 | Improved |
| use latent diffusion instead of pixel-space GLIDE | text-to-image · COCO | FID: 12.24 -> 12.63 | No clear effect |
Closest papers by meaning
- CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning (ICML 2025 · similarity 0.88)
- DuoGen: Towards Autonomous Interleaved Multimodal Generation (CVPR 2026 · similarity 0.88)
- MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models (NeurIPS 2025 · similarity 0.88)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.87)
- Fusion or Confusion? Multimodal Complexity Is Not All You Need (NeurIPS 2026 · similarity 0.87)
- PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor (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.
