Papers › Patch Craft: Video Denoising by Deep Modeling and Patch Matching

Patch Craft: Video Denoising by Deep Modeling and Patch Matching

25 Mar 2021ICCV 2021 10arXiv:2103.13767archive 2025-07-28

Gregory Vaksman, Michael Elad, Peyman Milanfar

The non-local self-similarity property of natural images has been exploited extensively for solving various image processing problems. When it comes to video sequences, harnessing this force is even more beneficial due to the temporal redundancy. In the context of image and video denoising, many classically-oriented algorithms employ self-similarity, splitting the data into overlapping patches, gathering groups of similar ones and processing these together somehow. With the emergence of convolutional neural networks (CNN), the patch-based framework has been abandoned. Most CNN denoisers operate on the whole image, leveraging non-local relations only implicitly by using a large receptive field. This work proposes a novel approach for leveraging self-similarity in the context of video denoising, while still relying on a regular convolutional architecture. We introduce a concept of patch-craft frames - artificial frames that are similar to the real ones, built by tiling matched patches. Our algorithm augments video sequences with patch-craft frames and feeds them to a CNN. We demonstrate the substantial boost in denoising performance obtained with the proposed approach.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2103.13767")

Code

Syntology Ran 4 of 8 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

grishavak/PaCNet-denoiser officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 4 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran
4unverified

Licence: 8 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from grishavak/PaCNet-denoiser. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

SepConvBnReM2D grishavak/PaCNet-denoiser/code/modules.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 1fd4e79013b2e149 · report
SepConvFM2D grishavak/PaCNet-denoiser/code/modules.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 7108e332e3a3a819 · report
SepConvOut2D grishavak/PaCNet-denoiser/code/modules.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · c147a5a5ed83c3f0 · report
SepConvOutB2D grishavak/PaCNet-denoiser/code/modules.py official repository ran no licence file found · pointer only · 1217c27913e87f5c · report
ResNn grishavak/PaCNet-denoiser/code/modules.py official repository unverified no licence file found · pointer only · c0fc554703db7da4 · report
SepConvNet2D grishavak/PaCNet-denoiser/code/modules.py official repository unverified no licence file found · pointer only · e4c5330a01499f3f · report
SepConvReF2D grishavak/PaCNet-denoiser/code/modules.py official repository unverified no licence file found · pointer only · efb53401376f2faa · report
VidCnn grishavak/PaCNet-denoiser/code/modules.py official repository unverified no licence file found · pointer only · 7a302576e2324c3e · report

Tasks

Color Image DenoisingDenoisingPatch MatchingVideo Denoising

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising CBSD68 sigma15 PaCNet PSNR 33.95 #7 of 10 Archive leaderboard report
Color Image Denoising CBSD68 sigma25 PaCNet PSNR 31.22 #6 of 9 Archive leaderboard report
Color Image Denoising CBSD68 sigma50 PaCNet PSNR 27.93 #13 of 18 Archive leaderboard report
Video Denoising DAVIS sigma10 PaCNet PSNR 39.97 #4 of 6 Archive leaderboard report
Video Denoising DAVIS sigma20 PaCNet PSNR 36.82 #4 of 7 Archive leaderboard report
Video Denoising DAVIS sigma30 PaCNet PSNR 34.79 #4 of 7 Archive leaderboard report
Video Denoising DAVIS sigma40 PaCNet PSNR 33.34 #5 of 8 Archive leaderboard report
Video Denoising DAVIS sigma50 PaCNet PSNR 32.2 #5 of 8 Archive leaderboard report
Video Denoising Set8 sigma10 PaCNet PSNR 37.06 #4 of 6 Archive leaderboard report
Video Denoising Set8 sigma20 PaCNet PSNR 33.94 #4 of 7 Archive leaderboard report
Video Denoising Set8 sigma30 PaCNet PSNR 32.05 #4 of 7 Archive leaderboard report
Video Denoising Set8 sigma40 PaCNet PSNR 30.7 #6 of 8 Archive leaderboard report
Video Denoising Set8 sigma50 PaCNet PSNR 29.66 #7 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections