Research map / Probabilistic and scientific modeling / Molecules and proteins
HLRTF: Hierarchical Low-Rank Tensor Factorization for Inverse Problems in Multi-Dimensional Imaging
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 |
|---|---|---|---|
| Replace the linear transform with a learned nonlinear DNN transform (ablation) | HLRTF for multi-dimensional image completion · Completion, WDC mall, sampling rate 0.1 | PSNR: 30.98 -> 45.71 | Helped |
| Increase the DNN depth from three layers to four (ablation) | HLRTF · Completion, WDC mall, sampling rate 0.1 | PSNR: 45.71 -> 45.68 | Hurt |
| Increase the DNN depth from three layers to five (ablation) | HLRTF · Completion, WDC mall, sampling rate 0.1 | PSNR: 45.71 -> 45.14 | Hurt |
| Add PTV regularization (ablation) | HLRTF · Completion, HSI, sampling rate 0.1 | PSNR: 41.11 -> 41.70 | Helped |
| Add PTV regularization (ablation) | HLRTF · Completion, MSI, sampling rate 0.1 | PSNR: 28.57 -> 32.13 | Helped |
| Add PTV regularization (ablation) | HLRTF · Denoising, MSI Balloons, Case 3 | PSNR: 24.49 -> 34.06 | Helped |
| Add PTV regularization (ablation) | HLRTF · Snapshot spectral imaging, HSI, sampling rate 0.1 | PSNR: 29.60 -> 30.90 | Helped |
| Use HLRTF instead of the strongest listed baseline | Multi-dimensional image completion · Completion, HSI, sampling rate 0.1 | PSNR: 40.35 -> 41.70 | Helped |
| Use HLRTF instead of the strongest listed baseline | Multi-dimensional image completion · Completion, MSI, sampling rate 0.1 | PSNR: 27.44 -> 32.13 | Helped |
| Use HLRTF instead of the strongest listed baseline | Multi-dimensional image denoising · Denoising, HSI, Case 1 | PSNR: 34.47 -> 32.75 | Mixed |
| Use HLRTF instead of the strongest listed baseline | Snapshot spectral imaging · Snapshot spectral imaging, HSI, sampling rate 0.1 | PSNR: 29.04 -> 30.90 | Helped |
Closest papers by meaning
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.90)
- OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems (AAAI 2025 · similarity 0.90)
- Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery (CVPR 2026 · similarity 0.88)
- Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction (CVPR 2021 · similarity 0.88)
- Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression (ICML 2025 · similarity 0.85)
- Non-Convex Tensor Recovery from Local Measurements (AAAI 2025 · 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.