mlsanityData to 7 Oct 2026

Clean Implicit 3D Structure from Noisy 2D STEM Images

arXiv 2203.15434 ↗First posted 29 Mar 2022eess.IV cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Scanning Transmission Electron Microscopes (STEMs) acquire 2D images of a 3D sample on the scale of individual cell components. Unfortunately, these 2D images can be too noisy to be fused into a useful 3D structure and facilitating good denoisers is challenging due to the lack of clean-noisy pairs. Additionally, representing a detailed 3D structure can be difficult even for clean data when using regular 3D grids. Addressing these two limitations, we suggest a differentiable image formation model for STEM, allowing to learn a joint model of 2D sensor noise in STEM together with an implicit 3D model. We show, that the combination of these models are able to successfully disentangle 3D signal and noise without supervision and outperform at the same time several baselines on synthetic and real data.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 70 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

27 of 70 references.

References · 27

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2015Variational Inference with Normalizing Flowscited by 2,161
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  8. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  9. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  10. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  11. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  12. 2017Learned Primal-dual Reconstructioncited by 251
15 more
  1. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  2. 2017Image reconstruction by domain transform manifold learningcited by 231
  3. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  4. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  5. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
  6. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  7. 2021T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesiscited by 88
  8. 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
  9. 2018A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Imagescited by 70
  10. 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
  11. 2018Radon Inversion via Deep Learningcited by 35
  12. 2017Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completioncited by 31
  13. 2019TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networkscited by 25
  14. 2019Microscopy Image Restoration with Deep Wiener-Kolmogorov filterscited by 7
  15. 2018Inviwo -- A Visualization System with Usage Abstraction Levelscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.

3 papers.

  1. 2023High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fieldscited by 1
  2. 2022Differentiable Electron Microscopy Simulation: Methods and Applications for Visualizationcited by 0
  3. 2025CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopycited by 0