AI Paper Atlas

Research map / Video / Video segmentation and tracking

Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising

Bihan Wen, Yanjun Li, Luke Pfister, Yoram Bresler

ICCV 2017 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 50 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
add low-rank regularization to the adaptive sparse model (BM-TL to SALT) (ablation)SALT · TUT and ASU, all noise levelsPSNR (dB): 0.6 dB average improvement of SALT over BM-TLImproved
add adaptive sparse approximation to the low-rank model (BM-LR to SALT) (ablation)SALT · TUT and ASU, all noise levelsPSNR (dB): 0.2 dB average improvement of SALT over BM-LRImproved
replace fixed 3D DCT with online learned sparsifying transform (ablation)BM-TL · TUT and ASU, all noise levelsPSNR (dB): 3.1 dB average improvement of SALT over BM-DCTImproved
learned transform vs fixed DCT in sparse model, TUT sigma=20 (ablation)BM-TL · TUT dataset, noise sigma=20PSNR (dB): 31.15 -> 32.84Improved
SALT vs VBM4D, averaged over 26 test videosSALT · TUT and ASU, all noise levelsPSNR (dB): 1.3 dB improvement over VBM4DImproved
SALT vs VBM3D, averaged over 26 test videosSALT · TUT and ASU, all noise levelsPSNR (dB): 1.2 dB improvement over VBM3DImproved
SALT vs VIDOSAT, averaged over 26 test videosSALT · TUT and ASU, all noise levelsPSNR (dB): 1.0 dB improvement over VIDOSATImproved
SALT vs sKSVD, averaged over 26 test videosSALT · TUT and ASU, all noise levelsPSNR (dB): 1.6 dB improvement over sKSVDImproved
SALT vs fBM3D, averaged over 26 test videosSALT · TUT and ASU, all noise levelsPSNR (dB): 3.6 dB improvement over fBM3DImproved
SALT vs VIDOSAT on Gbicycle frame, sigma=20SALT · Gbicycle (TUT), sigma=20PSNR (dB): 31.80 -> 35.67Improved
SALT vs VBM4D on Stefan frame, sigma=20SALT · Stefan (ASU), sigma=20PSNR (dB): 28.56 -> 29.69Improved

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