AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Training-Free Ultra Small Model for Universal Sparse Reconstruction in Compressed Sensing

Chaoqing Tang, Huanze Zhuang, Gui Yun Tian, Zhenli Zeng, Yijie Ding, Wenzhong Liu, Lin Lin, Xiang Bai

TPAMI 2026 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · ECG, Sr=0.05Mean SSIM: 0.344 -> 0.549Improved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · EEG, Sr=0.05Mean SSIM: 0.254 -> 0.735Improved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · EEG, Sr=0.5Mean SSIM: 0.977 -> 0.980No clear effect
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · synthetic 1D, low Sr and high KrSSIM: 2 to 3 times SSIMImproved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · synthetic 1D, other regionsSSIM: similar accuracy to OMPNo clear effect
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · synthetic 1D, 1000 signalstime: 2 to 3 orders of magnitude less timeImproved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · WSN, Sr=0.05Time (s): IHT-GPU 0.191 vs CLOMP 0.319Hurt
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · UHD 3840x2160, Sr=0.1Mean SSIM: 0.219 -> 0.707Improved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · 4K image datasetspeedup: 117 and 29 times faster than OMP and IHT at Sr=0.1Improved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · 4K image dataset, Sr=0.5speedup: 552 and 23 times fasterImproved
replace OMP pseudo-inverse with learnable coefficients (CLOMP)OMP · FHD 1920x1080, Sr=0.5Time (s): 159.825 -> 0.268Improved
raise sampling rate SrCLOMP · 8 image datasetsMean SSIM improvement over baselines: 292%, 98%, 45% at Sr=0.1, 0.3, 0.5Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy