Research map / Image generation / Image restoration
Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction
Miaoyu Li, Ying Fu, Ji Liu, Yulun Zhang
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 pixel adaptive descent step in the data module (ablation) | PADUT baseline · KAIST simulated | PSNR (dB): 36.19 -> 36.37 | Improved |
| add FFT-based stage fusion (FFT-SF) (ablation) | PADUT with PA · KAIST simulated | PSNR (dB): 36.37 -> 36.84 | Improved |
| add Non-local Spectral Transformer (NST) (ablation) | PADUT with PA and FFT-SF · KAIST simulated | PSNR (dB): 36.84 -> 36.95 | Improved |
| fuse stages in frequency domain (FFT-SF) instead of concat (ablation) | PADUT-3stg · KAIST simulated | PSNR (dB): 36.60 -> 36.95 | Improved |
| fuse stages with FFT-SF instead of ISFF (ablation) | PADUT-3stg · KAIST simulated | PSNR (dB): 36.53 -> 36.95 | Improved |
| share parameters across stages (ablation) | PADUT-3stg · KAIST simulated | PSNR (dB): 36.95 -> 35.65 | Hurt |
| use PADUT-3stg instead of MST-L/CST-L end-to-end methods | HSI reconstruction · KAIST simulated | PSNR (dB): +0.8 dB | Improved |
Closest papers by meaning
- Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging (NeurIPS 2022 · similarity 0.90)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.87)
- Dual-Window Multiscale Transformer for Hyperspectral Snapshot Compressive Imaging (AAAI 2024 · similarity 0.87)
- In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging (CVPR 2024 · similarity 0.87)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.87)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (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.
