AI Paper Atlas

Research map / Video / Video segmentation and tracking

Exploring Temporal Frequency Spectrum in Deep Video Deblurring

Qi Zhu, Man Zhou, Naishan Zheng, Chongyi Li, Jie Huang, Feng Zhao

ICCV 2023 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 23 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 SPA alignment module (ablation)frequency-temporal deblurring network · DVDPSNR: 32.51 -> 33.25Improved
add multi-scale pyramid in SPA (ablation)SPA · DVDPSNR: 32.91 -> 33.25Improved
add frequency spectrum modulation in SPA (ablation)SPA · DVDPSNR: 33.03 -> 33.25Improved
add frequency-spatial attention in TEA fusion vs no attention (ablation)TEA fusion · DVDPSNR: 32.74 -> 33.25Improved
combine frequency and spatial attention vs spatial only (ablation)TEA fusion · DVDPSNR: 33.05 -> 33.25Improved
add frequency loss with weight 0.1 (ablation)full model · DVDPSNR: 33.09 -> 33.25Improved
raise frequency loss weight to 1 (ablation)full model · DVDPSNR: 33.25 -> 33.13Hurt
use compact Ours-small with 64 channelsfull model · DVDPSNR: 32.48 PSNR with 4.04M paramsMixed

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