Research map / Architectures and efficiency / RNNs and normalization
TenSR: Multi-Dimensional Tensor Sparse Representation
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 TenSR instead of BM4D | 3D multispectral image denoising · Columbia MSI Database test images, σ = 5 | PSNR: 47.72 vs 43.74 | Hurt |
| Use TenSR instead of BM4D | 3D multispectral image denoising · Columbia MSI Database test images, σ = 10 | PSNR: 44.33 vs 39.05 | Hurt |
| Use TenSR instead of BM4D | 3D multispectral image denoising · Columbia MSI Database test images, σ = 20 | PSNR: 40.70 vs 35.01 | Hurt |
| Use TenSR instead of BM4D | 3D multispectral image denoising · Columbia MSI Database test images, σ = 30 | PSNR: 38.46 vs 33.31 | Hurt |
| Use TenSR instead of TensorDL | 3D multispectral image denoising · Columbia MSI Database test images, σ = 50 | PSNR: 35.86 vs 31.38 | Hurt |
| Use TenSR instead of TensorDL | 3D multispectral image denoising · Columbia MSI Database test images, σ = 5 | SSIM: 0.9896 vs 0.9750 | Hurt |
| Use TenSR instead of TensorDL | 3D multispectral image denoising · Columbia MSI Database test images, σ = 10 | SSIM: 0.9800 vs 0.9264 | Hurt |
| Use TenSR instead of TensorDL | 3D multispectral image denoising · Columbia MSI Database test images, σ = 20 | SSIM: 0.9638 vs 0.8473 | Hurt |
| Use TenSR instead of TensorDL | 3D multispectral image denoising · Columbia MSI Database test images, σ = 30 | SSIM: 0.9482 vs 0.7837 | Hurt |
| Use TenSR instead of TensorDL | 3D multispectral image denoising · Columbia MSI Database test images, σ = 50 | SSIM: 0.9139 vs 0.7778 | Hurt |
| Replace 1D FISTA with tensor-based TISTA | Sparse coding for sampled 3D signal cubes · 12 × 12 × 31 sub-MSI, 1758 cubes | runtime (seconds): 15674 -> 247.7 | Helped |
| Replace 1D FISTA with tensor-based TISTA | Sparse coding for sampled 3D signal cubes · 16 × 16 × 31 sub-MSI, 3888 cubes | runtime (seconds): 35912 -> 556.2 | Helped |
Closest papers by meaning
- Efficient Multi-Dimensional Tensor Sparse Coding Using t-Linear Combination (AAAI 2018 · similarity 0.88)
- A Provable Approach for Double-Sparse Coding (AAAI 2018 · similarity 0.85)
- Sparse Coding for Third-Order Super-Symmetric Tensor Descriptors With Application to Texture Recognition (CVPR 2016 · similarity 0.85)
- SINR: Sparsity Driven Compressed Implicit Neural Representations (CVPR 2025 · similarity 0.83)
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.82)
- Sparse Dimensionality Reduction Revisited (ICML 2024 · similarity 0.82)
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.