Research map / Vision-language and multimodal / Cross-modal learning
Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared
Yafei Zhang, Meng Ma, Huafeng Li, Yu Liu
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 shared dictionary (replace conv encoder-decoder) (ablation) | dictionary-guided fusion under missing IR · FLIR | AG: 3.320 -> 4.363 | Improved |
| add LLM-based modulation (ablation) | dictionary-guided fusion under missing IR · FLIR | CE: 1.452 -> 0.619 | Improved |
| add LLM modulation on top of the dictionary (ablation) | dictionary-guided fusion under missing IR · FLIR | AG: 4.363 -> 4.518 | Improved |
| add joint dictionary on top of LLM modulation (ablation) | dictionary-guided fusion under missing IR · FLIR | SF: 11.175 -> 12.554 | Improved |
| dictionary kernel 3x3 to 5x5 (ablation) | dictionary-guided fusion under missing IR · FLIR | CE: 1.357 -> 0.596 | Improved |
| dictionary kernel 5x5 to 7x7 (ablation) | dictionary-guided fusion under missing IR · FLIR | Qcb: 0.435 -> 0.356 | Hurt |
| increase IV-DLB blocks from 1 to 2 (ablation) | dictionary-guided fusion under missing IR · FLIR | AG: 4.518 -> 4.529 | No clear effect |
| increase IV-DLB blocks from 1 to 2 (ablation) | dictionary-guided fusion under missing IR · FLIR | GFLOPs: 63.023 -> 120.795 | Hurt |
| increase IV-DLB blocks from 1 to 3 (ablation) | dictionary-guided fusion under missing IR · FLIR | CE: 0.596 -> 0.679 | Hurt |
| use full textual prompt instead of no prompt (ablation) | dictionary-guided fusion under missing IR · FLIR | CE: 1.016 -> 0.596 | Improved |
| use full prompt instead of simplified prompt (ablation) | dictionary-guided fusion under missing IR · FLIR | Qcb: 0.419 -> 0.435 | Improved |
| fuse with predicted IR instead of using visible only | dictionary-guided fusion under missing IR · M3FD detection | mAP: 0.931 -> 0.948 | Mixed |
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.
- EMMA — EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (ICLR 2025) · better on 3 of 3 shared results
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
- FreeFusion: Infrared and Visible Image Fusion via Cross Reconstruction Learning (TPAMI 2025 · similarity 0.87)
- Domain Adaptation Guided Infrared and Visible Image Fusion (AAAI 2026 · similarity 0.87)
- Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion (CVPR 2026 · similarity 0.87)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.86)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · similarity 0.85)
- Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning (CVPR 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.
