Research map / Image generation / Image restoration
RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion
Jianghan Xia, Hong Song, Jinfu Li, Yucong Lin, Shihan Ma, Jingfan Fan, Danni Ai, Tianyu Fu, Deqiang Xiao, Jian Yang
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 Multi-Granular Transformer encoder instead of plain Restormer encoder (ablation) | RegionFuse · MSRS test | VIF: 1.037 -> 1.063 | Improved |
| add MoRA instead of vanilla attention (ablation) | RegionFuse · MSRS test | VIF: 1.060 -> 1.063 | Improved |
| add RFCM instead of a convolutional layer (ablation) | RegionFuse · MSRS test | Qcb: 0.569 -> 0.601 | Improved |
| add load-balancing loss for first 5 epochs (ablation) | RegionFuse · MSRS test | VIF: 1.036 -> 1.063 | Improved |
| use region-adaptive instead of sample-adaptive fusion (ablation) | RegionFuse · MSRS test | Qcb: 0.584 -> 0.601 | Improved |
| use region-adaptive instead of sample-adaptive fusion (ablation) | RegionFuse · MSRS test | SF: 11.965 -> 12.115 | Mixed |
| use fused images from RegionFuse as detector input | YOLOv5s · M3FD detection | mAP@0.5 (%): 82.11 -> 86.50 | Improved |
| increase contrast factor k from 1.5 to 5.0 (stronger non-uniform exposure) | RegionFuse vs baselines · MSRS enhanced | SF, AG, VIF, Qabf | Improved |
| transfer to NIR-VIS fusion without fine-tuning | RegionFuse · VIS-NIR Scene | VIF: 1.10 -> 1.12 vs best baseline | Improved |
| RegionFuse versus CDDFuse on spatial frequency | RegionFuse · RoadScene | SF: 18.93 -> 18.73 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DDFM — DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion (ICCV 2023) · 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
- Domain Adaptation Guided Infrared and Visible Image Fusion (AAAI 2026 · similarity 0.89)
- P²Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation (ECCV 2026 · similarity 0.88)
- Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption (TPAMI 2024 · similarity 0.88)
- MobileFusion: Mobile-Friendly Infrared and Visible Image Fusion via Structural Re-parameterization (ICML 2026 · similarity 0.87)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.85)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · 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.
