Datasets › SIDD

SIDD (Smartphone Image Denoising Dataset)

Introduced by Abdelrahman Abdelhamed et al. in A High-Quality Denoising Dataset for Smartphone Cameras archive 2025-07-28

SIDD is an image denoising dataset containing 30,000 noisy images from 10 scenes under different lighting conditions using five representative smartphone cameras. Ground truth images are provided along with the noisy images.

Source: A High-Quality Denoising Dataset for Smartphone Cameras

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

24 shown of 24 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 245. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
AKDT: Adaptive Kernel Dilation Transformer for Effective Image Denoising 1 1 26 Feb 2025 not harvested
Single Stage Adaptive Multi-Attention Network for Image Restoration 1 1 10 Apr 2024 not harvested
CascadedGaze: Efficiency in Global Context Extraction for Image Restoration 1 1 26 Jan 2024 ran 10 of 11 samples (1 unverified)
Dual Residual Attention Network for Image Denoising 1 1 7 May 2023 not harvested
KBNet: Kernel Basis Network for Image Restoration 1 1 6 Mar 2023 ran 6 of 9 samples (3 unverified)
Simple Baselines for Image Restoration 13 1 10 Apr 2022 ran 23 of 30 samples (7 unverified; 17 pointer-only for licence)
Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training 2 2 6 Apr 2022 ran 14 of 18 samples (4 unverified)
Selective Residual M-Net for Real Image Denoising 1 1 3 Mar 2022 not harvested
MAXIM: Multi-Axis MLP for Image Processing 3 1 9 Jan 2022 ran 27 of 46 samples (19 unverified)
Restormer: Efficient Transformer for High-Resolution Image Restoration 13 1 18 Nov 2021 ran 4 of 4 samples (0 unverified; 4 pointer-only for licence)
Uformer: A General U-Shaped Transformer for Image Restoration 4 1 6 Jun 2021 ran 6 of 6 samples (0 unverified; 2 pointer-only for licence)
HINet: Half Instance Normalization Network for Image Restoration 2 1 13 May 2021 not harvested
Multi-Stage Progressive Image Restoration 8 1 4 Feb 2021 ran 18 of 26 samples (8 unverified; 25 pointer-only for licence)
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection 9 1 30 Dec 2020 not harvested
Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation 2 2 12 Jul 2020 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
CycleISP: Real Image Restoration via Improved Data Synthesis 8 1 17 Mar 2020 not harvested
Learning Enriched Features for Real Image Restoration and Enhancement 12 1 15 Mar 2020 ran 3 of 20 samples (17 unverified; 3 pointer-only for licence)
Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization 1 1 26 Feb 2020 not harvested
Spatial-Adaptive Network for Single Image Denoising 2 1 28 Jan 2020 not harvested
Variational Denoising Network: Toward Blind Noise Modeling and Removal 2 1 29 Aug 2019 not harvested
GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling 2 1 27 May 2019 not harvested
Real Image Denoising with Feature Attention 3 1 16 Apr 2019 not harvested
Unprocessing Images for Learned Raw Denoising 4 1 27 Nov 2018 not harvested
Toward Convolutional Blind Denoising of Real Photographs 3 2 12 Jul 2018 ran 0 of 1 samples (1 unverified)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • SIDD

1 variant name, as the archive lists them.

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