AI Paper Atlas

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

Low-Rank Tensor Completion by Approximating the Tensor Average Rank

Zhanliang Wang, Junyu Dong, Xinguo Liu, Xueying Zeng

ICCV 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 12 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 TNN-DCT with the nonconvex tensor average rank surrogateDCT-based low-rank tensor completion · Standard images, sampling rate 0.2PSNR: 22.17 -> 23.01Improved
replace TNN-DCT with the nonconvex tensor average rank surrogateDCT-based low-rank tensor completion · CBSD68, sampling rate 0.8PSNR: 44.51 -> 44.74Improved
replace TNN-DCT with the nonconvex surrogate on a dynamic videoDCT-based low-rank tensor completion · Container video, sampling rate 0.4PSNR: 44.35 -> 45.66Improved
replace TNN-DCT with the nonconvex surrogateDCT-based low-rank tensor completion · Akiyo video, sampling rate 0.2PSNR: 36.40 -> 37.39Improved
use the closed-form hard thresholding algorithm instead of TNN-DCT's solvertensor completion · Standard imagesruntime (s): 4.59 -> 0.91Improved
replace TNN-DCT with the nonconvex surrogate on Containertensor completion · Container videoruntime (s): 27.02 -> 3.86Improved
use nonconvex surrogate instead of TNN-DCT in synthetic recovery at sampling rate 0.5synthetic tensor completion (n=40 and n=50) · Synthetic recovery phase transitionmax recoverable rank: four higher than that of TNN-DCTImproved
add coarse-to-fine continuation (adaptively decreasing lambda) instead of fixed small lambda (ablation)proposed tensor completion algorithm · Synthetic 10x10x10 tensor, average rank 1, sampling rate 0.5relative square error and convergence speedImproved
SPC at low sampling rate versus other baselinesSPC · Standard images, sampling rate 0.2PSNR: 24.51 vs 22.17 (TNN-DCT)Mixed

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