Research map / Image generation / Image restoration
Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion
Chunming He, Kai Li, Guoxia Xu, Yulun Zhang, Runze Hu, Zhenhua Guo, Xiu Li
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 proposed degradation-resistant fusion model (HIFM) instead of conventional model in a deep unfolding network (ablation) | DeRUN · IVF on M3FD | PSNR: 18.46 -> 18.73 | Improved |
| use deep unfolding network instead of ADMM solution (ablation) | HIFM · IVF on M3FD | PSNR: 16.23 -> 18.73 | Improved |
| add joint constraint strategy (physical and denoising constraints) (ablation) | DeRUN · IVF on M3FD | PSNR: 18.14 -> 18.73 | Improved |
| use partial weight sharing module instead of Siamesed extractor (ablation) | DeRUN · IVF on M3FD | PSNR: 18.24 -> 18.73 | Improved |
| use PWSM instead of symmetrical extractor with similar parameter count (ablation) | DeRUN · IVF on M3FD | PSNR: 18.57 -> 18.73 | Improved |
| add local gradient directional entropy loss (ablation) | DeRUN · IVF on M3FD | PSNR: 17.14 -> 18.73 | Improved |
| use LGDE loss instead of gradient penalty or joint gradient losses (ablation) | DeRUN · IVF on M3FD | PSNR: 18.67 -> 18.73 | Improved |
| use DeRUN fused images instead of single-modality inputs | YOLOv5 detector · M3FD | mAP@.5: 0.764 -> 0.819 | Improved |
| use DeRUN fused inputs for RGBT tracking | LADCF tracker · VOT-RGBT2019 | EAO: 0.257 -> 0.284 | Improved |
Closest papers by meaning
- MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion (NeurIPS 2026 · similarity 0.90)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.86)
- HUNet: Homotopy Unfolding Network for Image Compressive Sensing (CVPR 2025 · similarity 0.86)
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025 · similarity 0.86)
- Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks (CVPR 2025 · similarity 0.86)
- Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion (AAAI 2024 · similarity 0.84)
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.
