Research map / Architectures and efficiency / Attention and transformers
Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
Yuanhao Cai, Jing Lin, Haoqian Wang, Xin Yuan, Henghui Ding, Yulun Zhang, Radu Timofte, Luc Van Gool
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 DAUF (degradation-aware parameter estimation) to baseline (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 33.05 -> 35.37 | Improved |
| add HS-MSA to baseline (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 33.05 -> 35.49 | Improved |
| combine DAUF and HS-MSA (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 33.05 -> 37.21 | Improved |
| HS-MSA instead of global MSA (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 33.63 -> 34.05 | Improved |
| HS-MSA instead of Swin window MSA (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 33.75 -> 34.05 | Improved |
| HS-MSA instead of spectral-wise MSA (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 33.82 -> 34.05 | Improved |
| DAUF instead of DNU unfolding framework (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 34.62 -> 37.21 | Improved |
| DAUF instead of GAP framework (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 35.58 -> 37.21 | Improved |
| estimate alpha (projection scale) with estimator (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 36.49 -> 36.94 | Improved |
| feed beta (noise level) into denoiser (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 36.49 -> 36.83 | Improved |
| use both alpha and beta (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 36.49 -> 37.21 | Improved |
| increase unfolding stages from 3 to 9 (ablation) | DAUHST-3stg · KAIST simulation | PSNR: 37.21 -> 38.36 | Improved |
Closest papers by meaning
- Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging (CVPR 2023 · similarity 0.92)
- Dual-Window Multiscale Transformer for Hyperspectral Snapshot Compressive Imaging (AAAI 2024 · similarity 0.90)
- Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging (ECCV 2024 · similarity 0.90)
- SAH-SCI: Self-Supervised Adapter for Efficient Hyperspectral Snapshot Compressive Imaging (ECCV 2024 · similarity 0.90)
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.89)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · 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.
