Research map / Learning theory and algorithms / Matrix and tensor methods
Deeply Learned Spectral Total Variation Decomposition
Tamara G. Grossmann, Yury Korolev, Guy Gilboa, Carola Schoenlieb
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 |
|---|---|---|---|
| Replace the repeated model-driven TV-flow optimization with a trained TVspecNET | TV spectral decomposition · MS COCO test, 1024 × 1024 pixels | computation time (seconds): 28.2811 -> 0.0020 | Improved |
| Use an FFDnet basis network instead of DnCNN (ablation) | TVspecNET · MS COCO test | SSIM: 0.9600 -> 0.9377 | Hurt |
| Use a U-Net basis network instead of DnCNN (ablation) | TVspecNET · MS COCO test | SSIM: 0.9600 -> 0.9233 | Hurt |
| Add the band-sum reconstruction loss to MSE (ablation) | TVspecNET · MS COCO test | SSIM: 0.9600 -> 0.9639 | No clear effect |
| Add the normalized gradient Huber loss to MSE (ablation) | TVspecNET · MS COCO test | SSIM: 0.9600 -> 0.9559 | No clear effect |
| Add band-sum reconstruction and gradient Huber losses to MSE (ablation) | TVspecNET · MS COCO test | SSIM: 0.9600 -> 0.9619 | No clear effect |
| Train additionally on isolated disk eigenfunctions (ablation) | TVspecNET · Disk images | spectral band recovery | No clear effect |
| Train additionally on disk images (ablation) | TVspecNET · MS COCO test | SSIM: 0.9600 -> 0.9533 | Hurt |
Closest papers by meaning
- DNU: Deep Non-Local Unrolling for Computational Spectral Imaging (CVPR 2020 · similarity 0.88)
- Neural Spectral Decomposition for Dataset Distillation (ECCV 2024 · similarity 0.86)
- Self-Supervised Neural Networks for Spectral Snapshot Compressive Imaging (ICCV 2021 · similarity 0.86)
- FRN: Fractal-Based Recursive Spectral Reconstruction Network (NeurIPS 2025 · similarity 0.84)
- Any-Resolution AI-Generated Image Detection by Spectral Learning (CVPR 2025 · similarity 0.84)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (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.
