Research map / Image generation / Text-to-image diffusion
Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization
Weijian Su, Songqian Zhang, Yuqi Han, Jian Zhuang, Yongdong Huang, Qiang Zhang
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 joint conditional loss instead of single-objective L_ST (ablation) | PALDM · LLVIP | SD: 58.215 -> 60.806 | Improved |
| use joint conditional loss instead of multi-objective L_ET (ablation) | PALDM · LLVIP | SD: 53.612 -> 60.806 | Improved |
| use IDPO instead of standard DPO (ablation) | PCLDM · LLVIP | SD: 57.089 -> 61.911 | Improved |
| use IDPO instead of contrastive preference loss (ablation) | PCLDM · LLVIP | SD: 51.077 -> 61.911 | Improved |
| use IDPO instead of standard DPO (ablation) | PCLDM · LLVIP | AG: 14.215 -> 5.977 | Hurt |
| use IDPO instead of contrastive preference loss (ablation) | PCLDM · LLVIP | CNNIQA: 0.694 -> 0.655 | Hurt |
| add IDPO fine-tuning with segmentation preferences (ablation) | PCLDM · MSRS segmentation | mIoU: 55.21 -> 55.96 | Improved |
| use IDPO instead of standard DPO (ablation) | PCLDM · MSRS segmentation | mIoU: 55.20 -> 55.96 | Improved |
| add IDPO fine-tuning with segmentation preferences (ablation) | PCLDM · MSRS segmentation | mAcc: 63.52 -> 64.26 | Improved |
| add RLHF human-preference IDPO fine-tuning (ablation) | PALDM · LLVIP | SD: 60.806 -> 61.911 | Improved |
| add RLHF human-preference IDPO fine-tuning (ablation) | PALDM · RoadScene | SD: 45.137 -> 40.535 | Hurt |
| add RLVF VLM-preference IDPO fine-tuning (ablation) | PALDM · RoadScene | SD: 45.137 -> 53.323 | Improved |
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.
- Text-IF — Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion (CVPR 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
- D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples (ICML 2025 · similarity 0.87)
- Efficient Rectified Flow for Image Fusion (NeurIPS 2025 · similarity 0.86)
- MRFS: Mutually Reinforcing Image Fusion and Segmentation (CVPR 2024 · similarity 0.86)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.86)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · similarity 0.86)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.86)
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.
