Research map / Learning theory and algorithms / Matrix and tensor methods
Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery
Yisi Luo, Xi-Le Zhao, Zhemin Li, Michael K. Ng, Deyu Meng
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 |
|---|---|---|---|
| evaluate on a 2x denser hyperparameter grid via continuous representation (ablation) | LRTFR · HPO (data variance 0.25) | ACA: 75.50 -> 76.06 | Improved |
| evaluate on a 4x denser hyperparameter grid via continuous representation (ablation) | LRTFR · HPO (data variance 0.25) | ACA: 75.50 -> 76.04 | Improved |
| use sine activation instead of ReLU, LeakyReLU or Tanh (ablation) | LRTFR MLPs · image inpainting | PSNR | Improved |
| use Tucker function factorization instead of CP (ablation) | LRTFR · image inpainting | PSNR | Improved |
| replace discrete low-rank tensor HLRTF with LRTFR | image inpainting · Color images inpainting (SR 0.1) | PSNR: 22.49 -> 24.88 | Improved |
| replace INR-based SAPCU with LRTFR | point cloud upsampling · Point cloud upsampling (Bunny) | Chamfer distance: 0.0518 -> 0.0445 | Improved |
| replace supervised SDeCNN with unsupervised LRTFR under mixed noise | HSI denoising · HSI denoising (Case 5) | PSNR: 25.00 -> 34.09 | Improved |
Closest papers by meaning
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.90)
- Functional Transform-Based Low-Rank Tensor Factorization for Multi-Dimensional Data Recovery (ECCV 2024 · similarity 0.90)
- DELTA: Deep Low-Rank Tensor Representation for Multi-Dimensional Data Recovery (TPAMI 2025 · similarity 0.90)
- Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach (ICCV 2017 · similarity 0.89)
- Low-Rank Tensor Completion by Approximating the Tensor Average Rank (ICCV 2021 · similarity 0.88)
- Low-Rank Tensor Completion with Total Variation for Visual Data Inpainting (AAAI 2017 · similarity 0.88)
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.
