Research map / Image generation / Super-resolution
TRT: Harnessing Tensor Ring Transformer for Hyperspectral Image Super-Resolution
Honghui Xu, Junwei Zhu, Yubin Gu, Yueqian Quan, Chuangjie Fang, Hong Qiu, Jianwei Zheng
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 |
|---|---|---|---|
| reformulate HSISR as RPCA denoising instead of modeling spatial degradation with 3x3 conv (ablation) | TRT · Pavia (8x SR) | PSNR: 48.6395 -> 48.7409 | Improved |
| reformulate as RPCA instead of 3x3+5x5 multiscale spatial degradation (ablation) | TRT · Pavia (8x SR) | SAM: 3.1241 -> 3.0260 | Improved |
| reformulate as RPCA instead of 5x5 spatial degradation conv (ablation) | TRT · Pavia (8x SR) | ERGAS: 0.8298 -> 0.8139 | Improved |
| use TRT vs CYformer | TRT · Chikusei (8x SR) | PSNR: 41.9340 -> 42.7128 | Improved |
| use TRT vs DCINN | TRT · Pavia (4x SR) | PSNR: 48.2246 -> 49.4814 | Improved |
| use TRT vs best baseline | TRT · Cave (4x SR) | PSNR: 52.7989 -> 52.9614 | Improved |
| use TR-Transformer instead of Swin-Transformer prior (ablation) | TRT · Chikusei and Pavia (8x SR) | all metrics | Improved |
| use TR-Transformer instead of FLatten/Agent linear attention (ablation) | TRT · Chikusei and Pavia (8x SR) | complexity and quality | Improved |
| increase unfolding stages beyond 3-4 (ablation) | TRT · Chikusei | PSNR | No clear effect |
Closest papers by meaning
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.88)
- Hyperspectral Image Super-Resolution via Non-Local Sparse Tensor Factorization (CVPR 2017 · similarity 0.87)
- Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution (CVPR 2018 · similarity 0.87)
- Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction (CVPR 2021 · similarity 0.86)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.86)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · similarity 0.85)
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.
