Research map / Image generation / Image restoration
Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use LLRT rather than ISTReg | CAVE MSI denoising · CAVE, noise levels 10, 30, 50, and 100 | PSNR: 45.77 -> 46.67; 40.51 -> 41.55; 37.75 -> 38.93; 33.01 -> 35.40 | Helped |
| Use LLRT rather than ISTReg | CAVE MSI denoising · CAVE, noise levels 10, 30, 50, and 100 | SAM: 0.1086 -> 0.0841; 0.1374 -> 0.1192; 0.1619 -> 0.1424; 0.2376 -> 0.1895 | Helped |
| Use LLRT rather than CBM3D | BSD color image denoising · BSD, noise levels 10, 20, 30, and 40 | PSNR: 35.90 -> 36.04; 31.85 -> 32.00; 29.69 -> 29.87; 28.10 -> 28.50 | Helped |
| Use LLRT rather than CBM3D | BSD color image denoising · BSD, noise levels 10, 20, 30, and 40 | SSIM: 0.9501 -> 0.9513; 0.8923 -> 0.8957; 0.8402 -> 0.8434; 0.7872 -> 0.7992 | Helped |
| Add the spectral hyper-Laplacian prior (ablation) | LLRT · CAVE Flower, noise level 20 | PSNR: 34.30dB -> 34.95dB | Helped |
| Add the spectral hyper-Laplacian prior (ablation) | LLRT · CAVE Flower, noise level 20 | SSIM: 0.9097 -> 0.9225 | Helped |
| Increase the number of non-local cubics K (ablation) | LLRT · CAVE simulated denoising | PSNR | Helped |
| Increase the number of spectral bands B (ablation) | LLRT · CAVE simulated denoising | PSNR | Helped |
| Use LLRT rather than ISTReg | 512*512*31 multispectral image · Computational efficiency comparison | running time (seconds): 2103 -> 1093 | Helped |
Closest papers by meaning
- Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising (CVPR 2019 · similarity 0.93)
- Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization (CVPR 2016 · similarity 0.92)
- Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction (CVPR 2021 · similarity 0.88)
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.87)
- OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems (AAAI 2025 · similarity 0.86)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 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.