Research map / Vision-language and multimodal / Cross-modal learning
CO²IF: Language-Bridging Hyperspectral-Multispectral Image Fusion with Coordinated and Cross-modal Optimal Transport
Mingjin Zhang, Zhongkai Yang, Fei Gao
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 COT module (ablation) | CO2IF · CAVE | PSNR: 48.26 -> 50.25 | Improved |
| add COT module (ablation) | CO2IF · CAVE | SAM: 2.023 -> 1.436 | Improved |
| use optimal transport instead of cross-entropy loss (ablation) | CO2IF · CAVE | PSNR: 48.78 -> 50.25 | Improved |
| add G-constrained cost matrix to COT (ablation) | CO2IF · CAVE | PSNR: 49.68 -> 50.25 | Improved |
| use CoMamba instead of convolution (ablation) | CO2IF · CAVE | PSNR: 48.32 -> 50.25 | Improved |
| use CoMamba instead of cross-attention (ablation) | CO2IF · CAVE | PSNR: 48.81 -> 50.25 | Improved |
| use CoMamba instead of Cobra concatenation Mamba (ablation) | CO2IF · CAVE | PSNR: 49.45 -> 50.25 | Improved |
| add adaptive semantic weight matrix W (ablation) | CO2IF · CAVE | PSNR: 49.83 -> 50.25 | Improved |
| use CoMamba instead of cross-attention (compute cost) (ablation) | CO2IF · CAVE | FLOPs (G): 124.55 -> 106.67 | Improved |
| set lambda to 0.1 instead of 0.01 (ablation) | CoMamba · CAVE | PSNR: 49.41 -> 50.25 | Improved |
| set gamma to 0.1 instead of 0.2 (ablation) | CoMamba · CAVE | PSNR: 49.87 -> 50.25 | Improved |
| use text and HR-MSI together instead of removing text (ablation) | CO2IF · CAVE | PSNR | Improved |
Closest papers by meaning
- Unsupervised Hyperspectral Image Super-Resolution via Self-Supervised Modality Decoupling (IJCV 2026 · similarity 0.89)
- Hyperspectral and Multispectral Image Fusion with Arbitrary Resolution Through Self-Supervised Representations (IJCV 2025 · similarity 0.89)
- MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration (ICCV 2025 · similarity 0.88)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.87)
- Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis (CVPR 2024 · similarity 0.86)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · 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.
