Research map / Architectures and efficiency / Attention and transformers
Hybrid Spectral Denoising Transformer with Guided Attention
Zeqiang Lai, Chenggang Yan, Ying Fu
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 spectral self-attention across bands to a conv baseline (ablation) | HSDT-M · ICVL Gaussian sigma=50 | PSNR: 38.28 -> 41.34 | Improved |
| add learnable-query guidance to spectral attention (ablation) | HSDT-M · ICVL Gaussian sigma=50 | PSNR: 41.34 -> 41.46 | Improved |
| add self-modulated FFN (ablation) | HSDT-M · ICVL Gaussian sigma=50 | PSNR: 41.46 -> 41.62 | Improved |
| replace Conv3D with S3Conv (ablation) | HSDT-M · ICVL Gaussian sigma=50 | PSNR: 41.62 -> 41.82 | Improved |
| use GSSA instead of MDTA, QRU, GSA/MS-MSA or MGSA (ablation) | HSDT-M · ICVL Gaussian sigma=50 | PSNR: 41.03 -> 41.82 vs MDTA; 39.74 -> 41.82 vs MGSA | Improved |
| use S3Conv instead of previous separable conv Sep3D (ablation) | HSDT-M · ICVL Gaussian sigma=50 | PSNR: 41.44 -> 41.82 | Improved |
| implement GSSA with depthwise conv instead of matmul (ablation) | GSSA · ICVL Gaussian sigma=50 | runtime (s): 0.60 -> 0.47 s, PSNR 41.82 unchanged | Improved |
| sequential rather than parallel spatial/spectral convs in S3Conv (ablation) | S3Conv · ICVL Gaussian sigma=50 | PSNR: 41.82 -> 41.58 | Hurt |
| HSDT-L versus SST on impulse and mixture noise structure metrics | HSDT-L · ICVL complex noise (mixture) | SAM: SAM 0.101 vs SST 0.067 | Hurt |
Closest papers by meaning
- Spatial-Spectral Transformer for Hyperspectral Image Denoising (AAAI 2023 · similarity 0.94)
- VolFormer: Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond (CVPR 2025 · similarity 0.88)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.87)
- Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification (CVPR 2024 · similarity 0.87)
- LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift (NeurIPS 2026 · similarity 0.87)
- Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising (CVPR 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.
