Research map / Learning theory and algorithms / Matrix and tensor methods
Beyond RPCA: Flattening Complex Noise in the Frequency Domain
Read the paperCheck 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 |
|---|---|---|---|
| model noise in the frequency domain (FRPCA) instead of l1 sparse noise in spatial domain (RPCA) | RPCA · Synthetic, mixed complex noise | PSNR (dB): 24.67 -> 26.67 | Helped |
| frequency-domain noise model vs RPCA on sparse noise | RPCA · Synthetic, sparse noise | PSNR (dB): 27.91 -> 30.38 | Helped |
| frequency-domain noise model vs RPCA on Gaussian noise | RPCA · Synthetic, Gaussian noise | RRE: 0.0708 -> 0.0506 | Helped |
| frequency-domain noise model vs RPCA on running time, mixed complex noise | RPCA · Synthetic, mixed complex noise | time (s): 909.30 -> 416.84 | Helped |
| replace nuclear norm with truncated nuclear norm (r=10) (ablation) | FRPCA · Synthetic, sparse noise | PSNR (dB): 30.38 -> 30.48 | Helped |
| replace nuclear norm with truncated nuclear norm (r=10) (ablation) | FRPCA · Video background subtraction (qualitative) | visual quality | Hurt |
| increase truncation rank r from 10 to 20 in TFRPCA (ablation) | TFRPCA · Synthetic data | PSNR | Hurt |
Closest papers by meaning
- Manifold denoising by Nonlinear Robust Principal Component Analysis (NeurIPS 2019 · similarity 0.88)
- Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection (NeurIPS 2021 · similarity 0.87)
- RES-PCA: A Scalable Approach to Recovering Low-Rank Matrices (CVPR 2019 · similarity 0.87)
- Robust Formulation for PCA: Avoiding Mean Calculation With L2,p-norm Maximization (AAAI 2018 · similarity 0.87)
- Adaptive Rank Estimate in Robust Principal Component Analysis (CVPR 2021 · similarity 0.86)
- Capturing the denoising effect of PCA via compression ratio (NeurIPS 2024 · similarity 0.85)
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.