AI Paper Atlas

Research map / Video / Video segmentation and tracking

Plug-and-Play Algorithms for Video Snapshot Compressive Imaging

Xin Yuan, Yang Liu, Jinli Suo, Frédo Durand, Qionghai Dai

TPAMI 2021 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 128 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
use video denoiser FastDVDnet instead of image denoiser FFDNet (temporal correlation) (ablation)PnP-GAP · Grayscale benchmarkPSNR (dB): 29.70 -> 32.35Improved
use color denoising for joint reconstruction and demosaicing instead of grayscale denoising (ablation)PnP-FFDNet · Mid-scale color BayerPSNR (dB): 28.93 -> 32.38Improved
use color denoising for joint reconstruction and demosaicing instead of grayscale denoising (ablation)PnP-FastDVDnet · Mid-scale color BayerPSNR (dB): 30.50 -> 34.60Improved
replace TV prior with PnP-FFDNet denoiser (ablation)GAP · Grayscale benchmarkPSNR (dB): 26.73 -> 29.70Improved
combine WNNM with FFDNet instead of WNNM alone (DeSCI) (ablation)DeSCI · Grayscale benchmarkrun time (min): 103.0 -> 17.9Improved
replace WNNM with FastDVDnetDeSCI · Grayscale benchmarkPSNR (dB): 32.65 -> 32.35Mixed
add WNNM to FFDNet denoiser (ablation)PnP-FFDNet · Grayscale benchmarkPSNR (dB): 29.70 -> 31.72Improved
add VBM4D to WNNM (ablation)PnP-WNNM · Grayscale benchmarkPSNR (dB): 32.14 -> 29.66Hurt
use Python implementation instead of MATLAB for FFDNet (ablation)PnP-FFDNet · Grayscale benchmarkPSNR (dB): 29.70 -> 29.21Hurt
use Python implementation instead of MATLAB for GAP-TV (ablation)GAP-TV · Grayscale benchmarkrun time (min): 0.07 -> 0.03Improved
use color denoising instead of grayscale denoising (ablation)PnP-FastDVDnet · Mid-scale color Bayerrun time (min): 0.33 -> 1.65Hurt

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