mlsanityData to 7 Oct 2026

Benchmarking Denoising Algorithms with Real Photographs

arXiv 1707.01313 ↗First posted 5 Jul 2017cs.CVcited by 209

Not on the map. Why?

Abstract (arXiv)

Lacking realistic ground truth data, image denoising techniques are traditionally evaluated on images corrupted by synthesized i.i.d. Gaussian noise. We aim to obviate this unrealistic setting by developing a methodology for benchmarking denoising techniques on real photographs. We capture pairs of images with different ISO values and appropriately adjusted exposure times, where the nearly noise-free low-ISO image serves as reference. To derive the ground truth, careful post-processing is needed. We correct spatial misalignment, cope with inaccuracies in the exposure parameters through a linear intensity transform based on a novel heteroscedastic Tobit regression model, and remove residual low-frequency bias that stems, e.g., from minor illumination changes. We then capture a novel benchmark dataset, the Darmstadt Noise Dataset (DND), with consumer cameras of differing sensor sizes. One interesting finding is that various recent techniques that perform well on synthetic noise are clearly outperformed by BM3D on photographs with real noise. Our benchmark delineates realistic evaluation scenarios that deviate strongly from those commonly used in the scientific literature.

Key facts. Cited by 209 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 57; 2023: 44; 2024: 31; 2025: 22; 2026: 19.

209 papers.

Sort:

By area:

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  3. 2021Multi-Stage Progressive Image Restorationcited by 813
  4. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  5. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  6. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  7. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  8. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  9. 2022Deep Generalized Unfolding Networks for Image Restorationcited by 119
  10. 2021Invertible Image Signal Processingcited by 94
  11. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 92
  12. 2022Cross Aggregation Transformer for Image Restorationcited by 92
38 more
  1. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 85
  2. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  3. 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
  4. 2021Physics-based Noise Modeling for Extreme Low-light Photographycited by 67
  5. 2021Mobile Computational Photography: A Tourcited by 62
  6. 2022Multitask AET with Orthogonal Tangent Regularity for Dark Object Detectioncited by 59
  7. 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
  8. 2023Masked Image Training for Generalizable Deep Image Denoisingcited by 57
  9. 2022C2N: Practical Generative Noise Modeling for Real-World Denoisingcited by 56
  10. 2022Realistic Blur Synthesis for Learning Image Deblurringcited by 51
  11. 2021Dynamic Attentive Graph Learning for Image Restorationcited by 48
  12. 2022Dancing under the stars: video denoising in starlightcited by 47
  13. 2022CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Imagecited by 45
  14. 2023Instance Segmentation in the Darkcited by 45
  15. 2021Rethinking Deep Image Prior for Denoisingcited by 38
  16. 2023Xformer: Hybrid X-Shaped Transformer for Image Denoisingcited by 37
  17. 2023LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoisingcited by 37
  18. 2021IDR: Self-Supervised Image Denoising via Iterative Data Refinementcited by 36
  19. 2023Spatially Adaptive Self-Supervised Learning for Real-World Image Denoisingcited by 33
  20. 2023Random Sub-Samples Generation for Self-Supervised Real Image Denoisingcited by 31
  21. 2023MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Networkcited by 30
  22. 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
  23. 2023Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branchescited by 29
  24. 2022Modeling sRGB Camera Noise with Normalizing Flowscited by 28
  25. 2022Learning the Degradation Distribution for Blind Image Super-Resolutioncited by 27
  26. 2022Adaptive Dynamic Filtering Network for Image Denoisingcited by 27
  27. 2022Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Onescited by 24
  28. 2022Variational Deep Image Restorationcited by 24
  29. 2024CU-Mamba: Selective State Space Models with Channel Learning for Image Restorationcited by 24
  30. 2022Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modelingcited by 23
  31. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  32. 2021FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noisecited by 22
  33. 2023Towards General Low-Light Raw Noise Synthesis and Modelingcited by 19
  34. 2021Joint Denoising and Demosaicking with Green Channel Prior for Real-world Burst Imagescited by 18
  35. 2022Learn from Unpaired Data for Image Restoration: A Variational Bayes Approachcited by 18
  36. 2022Face Deblurring using Dual Camera Fusion on Mobile Phonescited by 18
  37. 2022High Dynamic Range and Super-Resolution from Raw Image Burstscited by 18
  38. 2022Efficient Visual Computing with Camera RAW Snapshotscited by 18

50 most cited of 209 All 209 (JSON)