mlsanityData to 7 Oct 2026

Weak-signal extraction enabled by deep-neural-network denoising of diffraction data

arXiv 2209.09247 ↗First posted 19 Sep 2022eess.IV cond-mat.str-el cond-mat.supr-concited by 5

Not on the map. Why?

Abstract (arXiv)

Removal or cancellation of noise has wide-spread applications for imaging and acoustics. In every-day-life applications, denoising may even include generative aspects, which are unfaithful to the ground truth. For scientific use, however, denoising must reproduce the ground truth accurately. Here, we show how data can be denoised via a deep convolutional neural network such that weak signals appear with quantitative accuracy. In particular, we study X-ray diffraction on crystalline materials. We demonstrate that weak signals stemming from charge ordering, insignificant in the noisy data, become visible and accurate in the denoised data. This success is enabled by supervised training of a deep neural network with pairs of measured low- and high-noise data. We demonstrate that using artificial noise does not yield such quantitatively accurate results. Our approach thus illustrates a practical strategy for noise filtering that can be applied to challenging acquisition problems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 58 references that are in the map. First posted on arXiv 19 Sep 2022.

Builds on

16 of 58 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  6. 2019On the Convergence of Adam and Beyondcited by 834
  7. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  8. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  9. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  10. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  11. 2019Deep Learning on Image Denoising: An overviewcited by 128
  12. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 70
4 more
  1. 2021Deep learning-based statistical noise reduction for multidimensional spectral datacited by 9
  2. 2021Deep Time Series Models for Scarce Datacited by 8
  3. 2022A universal synthetic dataset for machine learning on spectroscopic datacited by 3
  4. 2021Blind microscopy image denoising with a deep residual and multiscale encoder/decoder networkcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 3.

5 papers.

  1. 2026NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?cited by 9
  2. 2026Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoisingcited by 6
  3. 2024Deep-learning real-time phase retrieval of imperfect diffraction patterns from X-ray free-electron laserscited by 3
  4. 2024Training-set-free two-stage deep learning for spectroscopic data de-noisingcited by 0
  5. 2026Restore What Matters: Lessons from Joint Restoration and Recognitioncited by 0