Research map / Image generation / Super-resolution
Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependence
Hongyuan Wang, Lizhi Wang, Jiang Xu, Chang Chen, Xue Hu, Fenglong Song, Youliang Yan
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 SD3D splitting strategy (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1761 -> 0.1700 | Improved |
| add DLRM module (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1761 -> 0.1733 | Improved |
| combine SD3D and DLRM (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1761 -> 0.1648 | Improved |
| use SD3D instead of spatial-wise or spectral-wise splitting (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1937 / 0.1740 -> 0.1648 | Improved |
| use spectral-wise discontinuous splitting with spatial continuity (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1769 -> 0.1648 | Improved |
| break spatial continuity (discontinuous in both dimensions) (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1648 -> 0.1739 | Hurt |
| constrain dependence map to low rank (k=12 instead of k=32) (ablation) | ECT (1-stage) · NTIRE 2022 | MRAE: 0.1701 -> 0.1648 | Improved |
| increase network stages from 2 to 3 (ablation) | ECT · NTIRE 2022 | MRAE: 0.1564 -> 0.1542 (latency 82 -> 124 ms) | Improved |
| ECT versus HySAT on inference time | ECT · NTIRE 2022 | latency (ms): 126 -> 82 | Improved |
Closest papers by meaning
- ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution (ICCV 2023 · similarity 0.91)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.90)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.90)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.90)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.89)
- Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification (CVPR 2024 · similarity 0.89)
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.
