AI Paper Atlas

Research map / Video / Video segmentation and tracking

Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers

Zixuan Fu, Lanqing Guo, Chong Wang, Yufei Wang, Zhihao Li, Bihan Wen

ECCV 2024 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 9 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
fine-tune only temporal modules instead of all parameters (ablation)TAP · DAVIS sigma=30PSNR (dB): 34.20 dB -> 34.84 dBImproved
fine-tune temporal modules progressively instead of jointly (ablation)TAP · DAVIS sigma=30PSNR (dB): 34.55 dB -> 34.84 dBImproved
repeat the whole fine-tuning process twice (ablation)TAP · DAVIS sigma=30PSNR (dB): 34.84 dB -> 34.86 dBNo clear effect
add progressive fine-tuned temporal modules to pre-trained NAFNetNAFNet image denoiser · DAVIS (Gaussian average)PSNR (dB): 34.20 -> 35.48Improved
add progressive fine-tuned temporal modules to pre-trained NAFNetNAFNet image denoiser · Set8 (Gaussian average)PSNR (dB): 32.43 -> 33.95Improved
TAP compared with unsupervised RDRF on CRVD indoorTAP · CRVD indoor rawPSNR (dB): 45.09 -> 45.15Improved
add temporal modules to NAFNetNAFNet image denoiser · Static toy dataset temporal coherenceMAE of adjacent frames (x10^-3): 16.5 -> 5.8Improved

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