Research map / Image generation / Image restoration
Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
Yu Shi, Yu Liu, Zhong-Cheng Wu, Juan Cheng, Huafeng Li, Xun Chen
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 |
|---|---|---|---|
| add joint constraint correction (ablation) | Ours · M3FD composite degradation | Q_AB/F: 0.1054 -> 0.2199 | Improved |
| add joint constraint correction (ablation) | Ours · M3FD composite degradation | Q_W: 0.4135 -> 0.6237 | Improved |
| add joint constraint correction (ablation) | Ours · M3FD composite degradation | Q_MI: 0.2322 -> 0.3732 | Improved |
| add joint constraint correction (ablation) | Ours · M3FD blur | Q_AB/F: 0.3233 -> 0.3698 | Improved |
| add joint constraint correction (ablation) | Ours · M3FD noise | Q_AB/F: 0.3759 -> 0.4083 | Improved |
| add joint constraint correction (ablation) | Ours · M3FD noise | Q_CB: 0.4386 -> 0.4206 | Hurt |
| add joint constraint correction (ablation) | Ours · Harvard PET-MRI blur | Q_AB/F: 0.2019 -> 0.3855 | Improved |
| add joint constraint correction (ablation) | Ours · Harvard PET-MRI blur | Q_W: 0.5232 -> 0.7885 | Improved |
| add joint constraint correction (ablation) | Ours · Harvard PET-MRI composite degradation | Q_MI: 0.6116 -> 0.6019 | Hurt |
| add joint constraint correction (ablation) | Ours · Harvard PET-MRI noise | Q_MI: 0.6185 -> 0.6171 | No clear effect |
| increase diffusion steps T from 1 to 3 (ablation) | Ours · M3FD composite degradation | Q_P: 0.0618 -> 0.0755 | Improved |
| increase diffusion steps T from 3 to 5 (ablation) | Ours · M3FD composite degradation | Q_MI: 0.3732 -> 0.3663 | Hurt |
Closest papers by meaning
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.88)
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025 · similarity 0.88)
- Conditional Controllable Image Fusion (NeurIPS 2024 · similarity 0.88)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · similarity 0.88)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (AAAI 2025 · similarity 0.87)
- Restabilizing Diffusion Models with Predictive Noise Fusion Strategy for Image Super-Resolution (AAAI 2025 · 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.
