Research map / Image generation / Super-resolution
Toward Stable, Interpretable, and Lightweight Hyperspectral Super-Resolution
Wen-jin Guo, Weiying Xie, Kai Jiang, Yunsong Li, Jie Lei, Leyuan Fang
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 the proposed coordination optimization method rather than MHFNet | HSI-SR · CAVE | PSNR: 37.3 -> 39.5 | Improved |
| use the proposed coordination optimization method rather than MHFNet | HSI-SR · Harvard | PSNR: 41.1 -> 42.4 | Improved |
| use the proposed coordination optimization method rather than MHFNet | HSI-SR · Chikusei | PSNR: 33.6 -> 33.7 | Improved |
| add coordination between degradation estimation and fusion (ablation) | HSI-SR · CAVE, PSF5 | PSNR: 32.56 -> 39.48 | Improved |
| add degradation estimation (ablation) | HSI-SR · CAVE, PSF5 | PSNR: 32.72 -> 39.48 | Improved |
| use explicit degradation estimation instead of convolution layers (ablation) | HSI-SR · CAVE, PSF5 | PSNR: 31.42 -> 39.48 | Improved |
| add test-time fine-tuning (ablation) | HSI-SR · CAVE, PSF5 | PSNR: 27.93 -> 39.48 | Improved |
| add pre-training before test-time adaptation (ablation) | HSI-SR · CAVE, PSF5 | PSNR: 30.97 -> 39.48 | Improved |
| fix the encoder and fine-tune only the decoder (ablation) | HSI-SR · CAVE, PSF5 | PSNR: 35.79 -> 39.48 | Improved |
| fix the encoder rather than fine-tuning the entire network (ablation) | HSI-SR · CAVE, PSF5 | Test Time (s): 28.2 -> 20.5 | Improved |
Closest papers by meaning
- Building Non-Uniform Degradation Model for Position-Aware Hyperspectral Image Fusion (TPAMI 2025 · similarity 0.90)
- Unsupervised Test-Time Adaptation Learning for Effective Hyperspectral Image Super-Resolution With Unknown Degeneration (TPAMI 2024 · similarity 0.89)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.87)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.87)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered 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)
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.
