Research map / Label-efficient and robust learning / Self-supervised and contrastive
Hyperspectral and Multispectral Image Fusion with Arbitrary Resolution Through Self-Supervised Representations
Ting Wang, Zipei Yan, Jizhou Li, Xi-Le Zhao, Chao Wang, Michael K. Ng
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 TV loss (ablation) | CLoRF · Pavia University | MPSNR: 41.48 -> 42.23 | Improved |
| add TV loss (ablation) | CLoRF · University of Houston | MPSNR: 39.04 -> 40.55 | Improved |
| use Sine activation instead of ReLU (ablation) | CLoRF · Pavia University | MPSNR: 25.92 -> 42.23 | Improved |
| use Sine activation instead of ReLU+PE (ablation) | CLoRF · Pavia University | MPSNR: 36.26 -> 42.23 | Improved |
| use Sine activation instead of Spder (ablation) | CLoRF · University of Houston | MPSNR: 39.16 -> 40.55 | Improved |
| increase downsampling ratio from 4 to 16 | CLoRF · Pavia University | MPSNR: 42.23 -> 41.11 | Hurt |
| blind estimation of PSF and SRF instead of semi-blind | CLoRF · Pavia University | MPSNR: 41.40 -> 38.98 | Hurt |
| self-supervised CLoRF versus supervised MCT-Net | CLoRF · Pavia Center | MPSNR: 41.82 -> 43.47 | Improved |
| CLoRF versus bicubic for arbitrary spatial upsampling | CLoRF · Pavia University (336,336,50) | MPSNR: 29.29 -> 29.22 | No clear effect |
| CLoRF versus bicubic for joint spectral and spatial upsampling | CLoRF · Pavia University (336,336,93) | MPSNR: 27.48 -> 28.61 | Improved |
| CLoRF versus bicubic for arbitrary spectral upsampling | CLoRF · Pavia University (168,168,61) | MPSNR: 37.64 -> 42.42 | Improved |
| CLoRF versus MSE-SURE on SAM at Pavia Center | CLoRF · Pavia Center | SAM: 3.51 -> 3.64 | Hurt |
Closest papers by meaning
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.90)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.89)
- Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network (AAAI 2024 · similarity 0.88)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.88)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.88)
- Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis (CVPR 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.
