Grayscale Image Denoising

Benchmarks archive 2025-07-28

41 leaderboard tables shown for this task, 41 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 41 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

3 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

Most implemented papers archive 2025-07-28

9 shown of 9 papers with code (13 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Restormer: Efficient Transformer for High-Resolution Image Restoration
  18 Nov 2021 13 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks.
• SwinIR: Image Restoration Using Swin Transformer
  23 Aug 2021 9 repositories listed Syntology ran 30 of 45 samples · 15 unverified · 5 pointer-only (licence)
  In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.
• Index Network
  11 Aug 2019 6 repositories listed
  By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data…
• Improving Image Restoration by Revisiting Global Information Aggregation
  8 Dec 2021 3 repositories listed
  Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.
• Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning
  2 Jun 2023 1 repository listed
  Nonlocal self-similarity within natural images has become an increasingly popular prior in deep-learning models.
• KBNet: Kernel Basis Network for Image Restoration
  6 Mar 2023 1 repository listed Syntology ran 6 of 9 samples · 3 unverified
  In this paper, we propose a kernel basis attention (KBA) module, which introduces learnable kernel bases to model representative image patterns for spatial information aggregation.
• Adversarial Distortion Learning for Medical Image Denoising
  29 Apr 2022 1 repository listed
  The proposed ADL consists of two auto-encoders: a denoiser and a discriminator.
• CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning
  5 Mar 2021 1 repository listed
  In addition, we leverage the model's interpretable construction to propose an augmentation of the network's thresholds that enables state-of-the-art blind denoising performance and near-perfect generalization on…
• LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
  17 Nov 2019 1 repository listed
  This work proposes a novel lightweight learnable architecture for image denoising, and presents a combination of supervised and unsupervised training of it, the first aiming for a universal denoiser and the second for…

Syntology lines on 3 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. Read from the graph 2026-09-24.