Browse State-of-the-Art › Video Denoising
Video Denoising
40 papers with code · 12 benchmarks · 7 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
12 leaderboard tables shown for this task, 12 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 12 until expanded.
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
7 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 89 · with a code link: 40 · where Syntology ran a sample: 12 (7 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 89 tagged: 7 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 89 of 89, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
1 Jul 2019 5 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture.
-
5 Jun 2022 4 repositories listed Syntology official (archive's flag): 4 ran · 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified (of 14 harvested samples) · 7 pointer-only (licence)Specifically, RVRT divides the video into multiple clips and uses the previously inferred clip feature to estimate the subsequent clip feature.
-
24 Nov 2017 4 repositories listedMany video enhancement algorithms rely on optical flow to register frames in a video sequence.
-
26 Oct 2021 3 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 10 pointer-only (licence)In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H.
-
26 Jan 2021 3 repositories listedWe present a spatial pixel aggregation network and learn the pixel sampling and averaging strategies for image denoising.
-
3 Nov 2014 3 repositories listed Syntology official: not harvested · 0 ran · 4 unverified (of 4 harvested samples)We study TV regularization, a widely used technique for eliciting structured sparsity.
-
5 May 2019 2 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Video inpainting aims to fill spatio-temporal holes with plausible content in a video.
-
15 Apr 2019 2 repositories listedMost of the classical denoising methods restore clear results by selecting and averaging pixels in the noisy input.
-
30 Nov 2018 2 repositories listedTo the best of our knowledge, this is the first successful application of a CNN to video denoising.
-
27 Mar 2025 1 repository listedTo address these issues, we propose DynamiCtrl, a novel framework for human animation in video DiT architecture.
-
Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising16 Dec 2024 1 repository listedThis results in suboptimal utilization of both inter-frame and intra-frame information, and it also neglects the potential of optical flow alignment under self-supervised conditions, leading to biased and insufficient…
-
10 Oct 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 2 pointer-only (licence)In this work, we introduce a more natural formulation of autoregressive long video generation by revisiting the noise level assumption in video diffusion models.
-
4 Oct 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples)In this work, we propose TURTLE to learn the truncated causal history model for efficient and high-performing video restoration.
-
17 Sep 2024 1 repository listedRecent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision.
-
12 Aug 2024 1 repository listedFurthermore, to enhance the adaptivity of GCP-ID to various image contents, we cast the noise estimation problem into a classification task and train an effective estimator based on convolutional neural networks (CNNs).
-
15 Jul 2024 1 repository listedFirst, to enable dual-modal generation and maximize the information exchange between video and depth generation, we propose a unified dual-modal U-Net, a parameter-sharing framework for joint video and depth denoising…
-
1 Jul 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)This paper introduces a method for zero-shot video restoration using pre-trained image restoration diffusion models.
-
13 Feb 2024 1 repository listedIn this paper, we propose a simple and effective one step GCP-based image denoising (GCP-ID) method, which aims to exploit the GCP for denoising in the sRGB space by integrating it into the classic nonlocal transform…
-
25 Dec 2023 1 repository listedExtensive experiments demonstrate the leading VJDD performance of our method in term of restoration accuracy, perceptual quality and temporal consistency.
-
24 Nov 2023 1 repository listedWe propose an approach to do learning in Gaussian factor graphs.
-
29 Mar 2023 1 repository listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness.
-
14 Jul 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Recent multi-output inference works propagate the bidirectional temporal feature with a parallel or recurrent framework, which either suffers from performance drops on the temporal edges of clips or can not achieve…
-
5 Jul 2022 1 repository listedDespite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy.
-
22 Jun 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)In this study, we propose a simple yet effective framework for video restoration.
-
12 Apr 2022 1 repository listedHowever, BiRNN is intrinsically offline because it uses backward recurrent modules to propagate from the last to current frames, which causes high latency and large memory consumption.
-
20 Feb 2022 1 repository listedIn video denoising, the adjacent frames often provide very useful information, but accurate alignment is needed before such information can be harnassed.
-
28 Jan 2022 1 repository listed Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping.
-
25 Mar 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 8 harvested samples) · 8 pointer-only (licence)Our algorithm augments video sequences with patch-craft frames and feeds them to a CNN.
-
9 Mar 2021 1 repository listedThen, a denoising stage removes the noise in the fused frame.
-
4 Mar 2021 1 repository listedWe propose to do this by first explicitly aligning the neighboring frames to the current frame using a convolutional neural network (CNN).
-
30 Nov 2020 1 repository listed
-
31 Mar 2020 1 repository listed
-
6 Jan 2020 1 repository listed
-
2 Jan 2020 1 repository listed
-
4 Jun 2019 1 repository listed
-
8 May 2019 1 repository listed
-
24 Apr 2019 1 repository listed
-
30 Nov 2018 1 repository listed
-
3 Oct 2017 1 repository listed
-
1 Oct 2017 1 repository listed
-
MotionPro: A Precise Motion Controller for Image-to-Video Generation26 May 2025 0 repositories listed
-
CIM-NET: A Video Denoising Deep Neural Network Model Optimized for Computing-in-Memory Architectures23 May 2025 0 repositories listed
-
UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance12 Apr 2025 0 repositories listed
-
Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable4 Apr 2025 0 repositories listed
-
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion15 Jan 2025 0 repositories listed
-
LLVD: LSTM-based Explicit Motion Modeling in Latent Space for Blind Video Denoising10 Jan 2025 0 repositories listed
-
Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion8 Jan 2025 0 repositories listed
-
Imagine360: Immersive 360 Video Generation from Perspective Anchor4 Dec 2024 0 repositories listed
-
Video Denoising in Fluorescence Guided Surgery14 Nov 2024 0 repositories listed
-
14 Nov 2024 0 repositories listed
-
Nonlinear Inverse Design of Mechanical Multi-Material Metamaterials Enabled by Video Denoising Diffusion and Structure Identifier20 Sep 2024 0 repositories listed
-
A Practical Gated Recurrent Transformer Network Incorporating Multiple Fusions for Video Denoising10 Sep 2024 0 repositories listed
-
Adapting MIMO video restoration networks to low latency constraints22 Aug 2024 0 repositories listed
-
Lightweight Video Denoising Using a Classic Bayesian Backbone7 Aug 2024 0 repositories listed
-
Cascading Refinement Video Denoising with Uncertainty Adaptivity5 Aug 2024 0 repositories listed
-
Unsupervised Microscopy Video Denoising17 Apr 2024 0 repositories listed
-
25 Mar 2024 0 repositories listed
-
VJT: A Video Transformer on Joint Tasks of Deblurring, Low-light Enhancement and Denoising26 Jan 2024 0 repositories listed
-
Space-Time Attention with Shifted Non-Local Search28 Sep 2023 0 repositories listed
-
Recurrent Self-Supervised Video Denoising with Denser Receptive Field7 Aug 2023 0 repositories listed
-
Unsupervised Coordinate-Based Video Denoising1 Jul 2023 0 repositories listed
-
Contrastive Learning for Low-light Raw Denoising5 May 2023 0 repositories listed
-
RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset1 May 2023 0 repositories listed
-
Unlocking Masked Autoencoders as Loss Function for Image and Video Restoration29 Mar 2023 0 repositories listed
-
Low Latency Video Denoising for Online Conferencing Using CNN Architectures17 Feb 2023 0 repositories listed
-
Skip-Attention: Improving Vision Transformers by Paying Less Attention5 Jan 2023 0 repositories listed
-
Gated Recurrent Unit for Video Denoising17 Oct 2022 0 repositories listed
-
Video Restoration with a Deep Plug-and-Play Prior6 Sep 2022 0 repositories listed
-
A Multi-scale Video Denoising Algorithm for Raw Image5 Sep 2022 0 repositories listed
-
25 Aug 2022 0 repositories listed
-
Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network4 Jul 2022 0 repositories listed
-
Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer30 Apr 2022 0 repositories listed
-
Self-supervision versus synthetic datasets: which is the lesser evil in the context of video denoising?25 Apr 2022 0 repositories listed
-
A qualitative investigation of optical flow algorithms for video denoising19 Apr 2022 0 repositories listed
-
8 Apr 2022 0 repositories listed
-
RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression18 Mar 2022 0 repositories listed
-
Neural Compression-Based Feature Learning for Video Restoration17 Mar 2022 0 repositories listed
-
Real-Time Video Super-Resolution by Joint Local Inference and Global Parameter Estimation6 May 2021 0 repositories listed
-
Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition22 Nov 2020 0 repositories listed
-
Diagnosing and Preventing Instabilities in Recurrent Video Processing10 Oct 2020 0 repositories listed
-
Exploiting Temporal Attention Features for Effective Denoising in Videos5 Aug 2020 0 repositories listed
-
Learning Model-Blind Temporal Denoisers without Ground Truths7 Jul 2020 0 repositories listed
-
Block-matching in FPGA24 Jun 2020 0 repositories listed
-
Self-Supervised training for blind multi-frame video denoising15 Apr 2020 0 repositories listed
-
Restore from Restored: Video Restoration with Pseudo Clean Video9 Mar 2020 0 repositories listed
-
GPU acceleration of NL-means, BM3D and VBM3D7 Feb 2020 0 repositories listed
-
Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise1 Oct 2019 0 repositories listed
-
Video Denoising and Enhancement via Dynamic Video Layering5 Oct 2017 0 repositories listed
-
Reweighted Low-Rank Tensor Decomposition based on t-SVD and its Applications in Video Denoising18 Nov 2016 0 repositories listed
Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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