Research map / Image generation / Image restoration
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening
Wele Gedara Chaminda Bandara, Vishal M. Patel
Check 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 |
|---|---|---|---|
| Use cross-feature multi-head soft-attention instead of bypassing MHFSA (ablation) | HyperTransformer · Pavia Center | CC: 0.981 -> 0.989 | Improved |
| Use 1 global descriptor instead of 16 (ablation) | HyperTransformer · Pavia Center | CC: 0.989 -> 0.975 | Hurt |
| Use 2 global descriptors instead of 16 (ablation) | HyperTransformer · Pavia Center | CC: 0.989 -> 0.976 | Hurt |
| Use 8 global descriptors instead of 16 (ablation) | HyperTransformer · Pavia Center | CC: 0.989 -> 0.987 | Hurt |
| Use 32 global descriptors instead of 16 (ablation) | HyperTransformer · Pavia Center | CC: 0.989 -> 0.988 | Hurt |
| Use 64 global descriptors instead of 16 (ablation) | HyperTransformer · Pavia Center | CC: 0.989 -> 0.987 | Hurt |
| Apply HyperTransformer at all three scales rather than at ×4 only (ablation) | HyperTransformer · Pavia Center | CC: 0.986 -> 0.989 | Improved |
| Add ×1 to the ×4 scale configuration (ablation) | HyperTransformer · Pavia Center | CC: 0.986 -> 0.988 | Improved |
| Add ×2 to the ×4 scale configuration (ablation) | HyperTransformer · Pavia Center | CC: 0.986 -> 0.988 | Improved |
| Add VGG perceptual loss to L1 training (ablation) | HyperTransformer · Pavia Center | CC: 0.987 -> 0.988 | Improved |
| Add transfer perceptual loss to L1 and VGG perceptual loss (ablation) | HyperTransformer · Pavia Center | CC: 0.988 -> 0.989 | Improved |
| Replace the strongest baseline with HyperTransformer | Pansharpening methods · Pavia Center | CC: 0.980 -> 0.989 | Improved |
Closest papers by meaning
- Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening (AAAI 2025 · similarity 0.89)
- Hyperspectral Pansharpening via Diffusion Models with Iteratively Zero-Shot Guidance (CVPR 2025 · similarity 0.88)
- FMPM-DNet: Hyperspectral Pansharpening Dynamic Network Based on Feature Modulation and Probability Mask (AAAI 2025 · similarity 0.87)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 2025 · similarity 0.87)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.86)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 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.
