Browse State-of-the-Art › Image Denoising

Image Denoising

509 papers with code · 21 benchmarks · 22 datasets archive 2025-07-28

Computer VisionMedical

Image Denoising is a computer vision task that involves removing noise from an image. Noise can be introduced into an image during acquisition or processing, and can reduce image quality and make it difficult to interpret. Image denoising techniques aim to restore an image to its original quality by reducing or removing the noise, while preserving the important features of the image.

( Image credit: Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

21 leaderboard tables shown for this task, 21 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 21 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): FMD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
SIDD (22 rows) CGNet CascadedGaze: Efficiency in Global Context Extraction for Image Restoration code Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified Compare
DND (16 rows) DualDn DualDn: Dual-domain Denoising via Differentiable ISP code — Compare
ELD SonyA7S2 x200 (10 rows) LLD* Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme... code — Compare
SID SonyA7S2 x250 (10 rows) LLD* Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme... code — Compare
ELD SonyA7S2 x100 (9 rows) LLD* Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme... code — Compare
SID x100 (8 rows) LLD* Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme... code — Compare
SID x300 (8 rows) LLD* Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme... code — Compare
SID SonyA7S2 x100 (5 rows) PMN Learnability Enhancement for Low-light Raw Denoising: Where Paired... code — Compare
urban100 sigma15 (4 rows) AKDT AKDT: Adaptive Kernel Dilation Transformer for Effective Image Denoising code — Compare
Urban100 sigma50 (4 rows) MaIR+ MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration code — Compare
BSD68 sigma50 (2 rows) MaIR+ MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration code — Compare
SID SonyA7S2 x300 (2 rows) LED Make Explicit Calibration Implicit: Calibrate Denoiser Instead of... code Syntology official (archive's flag): 8 ran · 8 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; 5 where Syntology's instrument failed) · 3 unverified Compare
Urban100 sigma25 (2 rows) MaIR+ MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration code — Compare
BSD68 sigma30 (1 row) R3L R3L: Connecting Deep Reinforcement Learning to Recurrent Neural... — — Compare
FFHQ (1 row) BRGM Bayesian Image Reconstruction using Deep Generative Models code — Compare
FFHQ 64x64 - 4x upscaling (1 row) BRGM Bayesian Image Reconstruction using Deep Generative Models code — Compare
FMD (1 row) NOise2NOise Machine learning for faster and smarter fluorescence lifetime... code — Compare
Image Denoising on SID x300 (1 row) ExposureDiffusion (UNet+paired data) ExposureDiffusion: Learning to Expose for Low-light Image Enhancement code — Compare
Nam (1 row) PNGAN Learning to Generate Realistic Noisy Images via Pixel-level... code Syntology 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified Compare
PolyU (1 row) PNGAN Learning to Generate Realistic Noisy Images via Pixel-level... code Syntology 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified Compare
ultracold fermions Technion system, pixelfly (1 row) absDL Single-exposure absorption imaging of ultracold atoms using deep learning code — Compare

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

22 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,220 · with a code link: 509 · where Syntology ran a sample: 89 (78 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (89 of 1,220 tagged: 78 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument)

Page 1 of 13: papers 1 to 100 of 1,220, 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.

Syntology lines on 36 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