Research map / Image generation / Autoregressive and latent generation
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
Zixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang, Shuang Xu, Yulun Zhang, Kai Zhang, Deyu Meng, Radu Timofte, Luc Van Gool
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 DDFM instead of DeFusion on medical image fusion | multi-modality image fusion · Harvard Medical Fusion | VIF: 0.62 -> 0.76 | Improved |
| use DDFM instead of RFNet on entropy | medical image fusion · Harvard Medical Fusion | EN: 4.75 (RFNet) vs 4.64 (DDFM) | Hurt |
| add the diffusion sampling framework on top of the EM solver (remove DDPM, keep EM only) (ablation) | DDFM · RoadScene (IVF) | six fusion metrics | Improved |
| add total variation penalty r(x) in the EM module (ablation) | DDFM · RoadScene (IVF) | six fusion metrics | Improved |
| infer phi via hierarchical Bayesian model instead of fixing phi to 0.1 or 1 with ADMM (ablation) | DDFM · RoadScene (IVF) | six fusion metrics | Improved |
Later papers that compared with this method
3 later accepted papers report DDFM as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion (CVPR 2026 · better on 1 of 1 shared result)
- Conditional Controllable Image Fusion (NeurIPS 2024 · better on 1 of 3 shared results)
- Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model (NeurIPS 2024 · 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
- A Modular Conditional Diffusion Framework for Image Reconstruction (NeurIPS 2024 · similarity 0.88)
- Conditional Controllable Image Fusion (NeurIPS 2024 · similarity 0.88)
- Learning Diffusion Texture Priors for Image Restoration (CVPR 2024 · similarity 0.88)
- Patched Denoising Diffusion Models For High-Resolution Image Synthesis (ICLR 2024 · similarity 0.88)
- Residual Denoising Diffusion Models (CVPR 2024 · similarity 0.88)
- UDPM: Upsampling Diffusion Probabilistic Models (NeurIPS 2024 · similarity 0.88)
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.
