AI Paper Atlas

Research map / Video / Video segmentation and tracking

Patch Craft: Video Denoising by Deep Modeling and Patch Matching

Gregory Vaksman, Michael Elad, Peyman Milanfar

ICCV 2021 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 70 citations (OpenAlex)

Read the paper

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
extend nearest neighbor search to 7 adjacent frames (T_s=3 instead of 0) (ablation)S-CNN · DAVIS average over sigma 10-50PSNR: 33.63 -> 35.01Improved
extend nearest neighbor search to adjacent frames, sigma=10 (ablation)S-CNN · DAVIS sigma=10PSNR: 38.38 -> 39.90Improved
extend nearest neighbor search to adjacent frames, sigma=50 (ablation)S-CNN · DAVIS sigma=50PSNR: 30.51 -> 31.55Improved
add T-CNN temporal filtering after S-CNN (ablation)PaCNet · DAVIS average over sigma 10-50PSNR: 35.01 -> 35.42Improved
add T-CNN temporal filtering, sigma=10 (ablation)PaCNet · DAVIS sigma=10PSNR: 39.90 -> 39.97Improved
add T-CNN temporal filtering, sigma=50 (ablation)PaCNet · DAVIS sigma=50PSNR: 31.55 -> 32.20Improved
patch-craft frames with CNN versus FastDVDnet (no explicit non-local similarity)PaCNet · DAVIS average over sigma 10-50PSNR: 34.74 -> 35.42Improved
benefit versus FastDVDnet shrinks as noise growsPaCNet · DAVIS sigma 10 vs 50PSNR: 38.93 -> 39.97; 31.90 -> 32.20Mixed
PaCNet versus FastDVDnet under clipped Gaussian noisePaCNet · DAVIS clipped noise averagePSNR: 34.51 -> 35.54Improved
PaCNet versus FastDVDnet on Set8PaCNet · Set8 averagePSNR: 32.31 -> 32.68Improved
single-frame S-CNN-0 versus LIDIA, a similar NN-augmented image denoiserS-CNN-0 · single image denoising averagePSNR: 31.11 -> 31.03No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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