AI Paper Atlas

Research map / Video / Video segmentation and tracking

Unsupervised Deep Video Denoising

Dev Yashpal Sheth, Sreyas Mohan, Joshua L. Vincent, Ramon Manzorro, Peter A. Crozier, Mitesh M. Khapra, Eero P. Simoncelli, Carlos Fernandez-Granda

ICCV 2021 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 74 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 5 input frames instead of 1 (ablation)UDVD · DAVIS test (sigma=30)PSNR: 32.80 -> 33.92Improved
use 5 input frames instead of 1 (ablation)UDVD · Set8 (sigma=30)PSNR: 30.91 -> 32.01Improved
use 5 input frames instead of 3 (ablation)UDVD · DAVIS test (sigma=30)PSNR: 33.48 -> 33.92Improved
use 5 input frames instead of 1 at high noise (ablation)UDVD · DAVIS test (sigma=80)PSNR: 28.37 -> 29.63Improved
add early stopping on held-out last 5 frames (ablation)UDVD-S · 9 videos (sigma=90)PSNR: 23.33 -> 27.60Improved
add early stopping on held-out last 5 frames (ablation)UDVD-S · 9 videos (sigma=30)PSNR: 30.80 -> 32.39Improved
add spatial flipping and time reversal augmentation (with early stopping) (ablation)UDVD-S · 9 videos (sigma=30)PSNR: 32.39 -> 32.61Improved
add spatial flipping and time reversal augmentation (with early stopping) (ablation)UDVD-S · 9 videos (sigma=90)PSNR: 27.60 -> 27.80Improved
add flip and time reversal augmentation (without early stopping) (ablation)UDVD-S · 9 videos (sigma=30)PSNR: 30.80 -> 32.24Improved
train UDVD on single video (UDVD-S) instead of DAVIS datasetUDVD · Set8 individual-video (sigma=30)PSNR: 31.90 -> 32.90Improved
train UDVD-S without pretraining instead of fine-tuning MF2FUDVD-S · Set8 individual-video (sigma=30)PSNR: 31.84 -> 32.90Improved
unsupervised UDVD instead of supervised RViDeNet on raw videoUDVD · Raw video datasetPSNR: 43.97 -> 44.69Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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