Research map / Image generation / Super-resolution
HSIGene: A Foundation Model for Hyperspectral Image Generation
Pang Li, Xiangyong Cao, Datao Tang, Shuang Xu, Xueru Bai, Feng Zhou, Deyu Meng
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 the RGAN second stage to DSRNet (ablation) | two-stage SR · HSI super-resolution | BRISQUE: 37.120 -> 15.572 | Improved |
| add the DSRNet diffusion stage to RGAN (ablation) | two-stage SR · HSI super-resolution | BRISQUE: 35.338 -> 15.572 | Improved |
| add super-resolved augmented data to training (ablation) | HSIGene · AID HED generation | BRISQUE: 36.898 -> 27.125 | Improved |
| add super-resolved augmented data to training (ablation) | HSIGene · AID Sketch generation | SSIM: 0.216 -> 0.265 | Improved |
| add super-resolved augmented data to training (ablation) | HSIGene · AID MLSD generation | sPr: 0.899 -> 0.872 | Hurt |
| add super-resolved augmented data to training (ablation) | HSIGene · AID MLSD generation | sRec: 0.925 -> 0.975 | Improved |
| add HED to MLSD conditions (ablation) | HSIGene · AID multi-condition generation | SSIM: 0.267 -> 0.359 | Improved |
| add segmentation to MLSD+HED+Sketch conditions (ablation) | HSIGene · AID multi-condition generation | sRec: 0.931 -> 0.852 | Hurt |
| add synthetic data to real data for training denoiser | TRQ3D · WHU-Hi-HanChuan denoising | PSNR: 24.355 -> 32.362 | Improved |
| add synthetic data to real data for training denoiser | SERT · WHU-Hi-HanChuan denoising | PSNR: 29.122 -> 34.762 | Improved |
| add synthetic data to real data for training denoiser | T3SC · Xiongan denoising | PSNR: 37.932 -> 38.227 | No clear effect |
| add synthetic data to real data for training denoiser | SSPSR · Xiongan super-resolution | PSNR: 37.485 -> 37.474 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports HSI-Gene as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors (ICML 2026 · better on 9 of 9 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
- Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network (AAAI 2024 · similarity 0.92)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.91)
- Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis (CVPR 2024 · similarity 0.90)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.89)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.88)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.88)
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.
