AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring

Jinshan Pan, Boming Xu, Jiangxin Dong, Jianjun Ge, Jinhui Tang

CVPR 2023 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 41 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 the proposed DSTNet instead of the strongest listed baselineVideo deblurring · DVDPSNR: 33.36 -> 33.79Improved
Add the channel-wise gated dynamic network (ablation)DSTNet · GoProPSNR: 33.18 -> 33.33Improved
Replace CWGDN with gMLP (ablation)DSTNet · GoProPSNR: 33.33 -> 33.16Hurt
Add gated feature fusion in DTFF (ablation)DSTNet · GoProPSNR: 33.22 -> 33.33Improved
Use DTFF gated feature fusion instead of feature fusion [27] (ablation)DSTNet · GoProPSNR: 33.00 -> 33.33Improved
Add pixel-wise filter estimation in DTFF (ablation)DSTNet · GoProPSNR: 32.55 -> 33.33Improved
Add wavelet-based feature propagation (ablation)DSTNet · GoProPSNR: 28.57 -> 33.33Improved
Use wavelet transforms instead of bilinear downsampling and upsampling in feature propagation (ablation)DSTNet · GoProPSNR: 32.87 -> 33.33Improved

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