AI Paper Atlas

Research map / Benchmarks / SIDD benchmark

SIDD benchmark leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SIDD benchmark. Best PSNR (dB): 40.23 (Condformer, IJCV 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

SIDD benchmark · PSNR (dB)

16 papers, each with its best reported number for its own method; higher is better.

6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SIDD benchmark · SSIM

16 papers, each with its best reported number for its own method; higher is better.

#SSIM ↑MethodPaperTopic
10.958ADFNetAdaptive Dynamic Filtering Network for Image Denoising
AAAI 2023 · Table: real-world image denois
Image restoration
20.957ScaoedNet†Enhanced Latent Space Blind Model for Real Image Denoising via Alternative Optimization
NeurIPS 2022 · Table 2
Image restoration
30.942AT-BSN (D)Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios
CVPR 2024 · Table 1
Self-supervised and contrastive
40.936LG-BPNLG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising
CVPR 2023 · Table 1
Self-supervised and contrastive
50.936PUCA (Ours)PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
NeurIPS 2023 · Table 1
Image restoration
60.935DnCNN trained with NAFlow noise
DnCNN
sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
ICLR 2024 · Table: Quantitative results of
Image restoration
70.934Ours
U-Net
Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising
CVPR 2023 · Table 1
Image restoration
80.934C-BSN
AP-BSN structure
Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network
ICCV 2023 · Table 1
Image restoration
90.932NeCA-W
DnCNN
sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model
CVPR 2023 · Table 2
Image restoration
100.925SCPGabNet
DeamNet
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
ICCV 2023 · Table 1
GANs
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.