Research map / Image generation / Image restoration
Physical Degradation Model-Guided Interferometric Hyperspectral Reconstruction with Unfolding Transformer
Yuansheng Li, Yunhao Zou, Linwei Chen, 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 physical noise model (shot+read, standard) instead of Gaussian white noise (ablation) | IHRUT-5 trained on synthetic data · Calibration (real) | PSNR: 37.95 -> 38.82 | Improved |
| add pixel-wise stripe-pattern noise modeling over standard noise (ablation) | IHRUT-5 · Calibration (real) | PSNR: 38.82 -> 39.28 | Improved |
| add electronic gain e for parameter randomization (ablation) | IHRUT-5 · Calibration (real) | PSNR: 39.28 -> 39.46 | Improved |
| add relative response coefficient M to optical degradation (ablation) | IHRUT-5 degradation model · Calibration (real) | PSNR: 26.20 -> 33.96 | Improved |
| add SPE_0 to the data module (ablation) | IHRUT-5 · Calibration (real) | PSNR: 34.37 -> 38.73 | Improved |
| add SPE_k to the data module (ablation) | IHRUT-5 · Calibration (real) | PSNR: 38.73 -> 39.10 | Improved |
| add momentum branch (ablation) | IHRUT-5 · Calibration (real) | PSNR: 39.10 -> 39.12 | Improved |
| add cross-stage fusion in prior module (ablation) | IHRUT-5 · Calibration (real) | PSNR: 39.12 -> 39.35 | Improved |
| add SPE in the prior module (ablation) | IHRUT-5 · Calibration (real) | PSNR: 39.35 -> 39.46 | Improved |
| use SPE_k(SPE_0*delta+m) instead of channel-attention momentum branch (CA*delta+CA(m)) (ablation) | IHRUT-5 data module · Calibration (real) | PSNR: 38.31 -> 39.46 | Improved |
| use IHRUT-5 instead of MAUN-7 on real data | unfolding methods · Calibration (real) | PSNR: 38.15 -> 39.46 | Improved |
| use IHRUT-7 instead of 5 stages | IHRUT · HSOD-BIT | PSNR: 44.25 -> 44.30 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.86)
- Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging (NeurIPS 2022 · similarity 0.86)
- In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging (CVPR 2024 · similarity 0.86)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.85)
- Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification (CVPR 2024 · similarity 0.84)
- Dual-Window Multiscale Transformer for Hyperspectral Snapshot Compressive Imaging (AAAI 2024 · similarity 0.84)
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.
