Research map / Architectures and efficiency / RNNs and normalization
DNU: Deep Non-Local Unrolling for Computational Spectral Imaging
Lizhi Wang, Chen Sun, Maoqing Zhang, Ying Fu, Hua Huang
Check 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 |
|---|---|---|---|
| Integrate learned local and non-local priors in an unrolled reconstruction network | DNU · ICVL | PSNR: 32.36 -> 34.27 | Improved |
| Integrate learned local and non-local priors in an unrolled reconstruction network | DNU · Harvard | PSNR: 31.13 -> 32.71 | Improved |
| Use DNU instead of the strongest reported baseline | DNU · ICVL | SSIM: 0.986 -> 0.991 | Improved |
| Use DNU instead of the strongest reported baseline | DNU · Harvard | SAM: 0.101 -> 0.091 | Improved |
| Use DNU instead of ISTA-Net | DNU · Set11, 10% | PSNR: 25.80 -> 25.96 | Improved |
| Use DNU instead of ISTA-Net | DNU · Set11, 4% | PSNR: 21.23 -> 22.11 | Improved |
| Use DNU instead of ISTA-Net | DNU · BSD68, 10% | PSNR: 25.02 -> 25.46 | Improved |
| Use DNU instead of ISTA-Net | DNU · BSD68, 4% | PSNR: 22.12 -> 22.94 | Improved |
| Add the non-local prior branch (ablation) | DNU spectral image prior network · ICVL | PSNR | Improved |
Closest papers by meaning
- Deeply Learned Spectral Total Variation Decomposition (NeurIPS 2020 · similarity 0.88)
- Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior (CVPR 2019 · similarity 0.88)
- Self-Supervised Neural Networks for Spectral Snapshot Compressive Imaging (ICCV 2021 · similarity 0.87)
- Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging (ECCV 2024 · similarity 0.87)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.86)
- FRN: Fractal-Based Recursive Spectral Reconstruction Network (NeurIPS 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.
