mlsanityData to 7 Oct 2026

Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields

arXiv 2112.00002 ↗First posted 27 Nov 2021eess.IV cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Intensity diffraction tomography (IDT) refers to a class of optical microscopy techniques for imaging the 3D refractive index (RI) distribution of a sample from a set of 2D intensity-only measurements. The reconstruction of artifact-free RI maps is a fundamental challenge in IDT due to the loss of phase information and the missing cone problem. Neural fields (NF) has recently emerged as a new deep learning (DL) approach for learning continuous representations of physical fields. NF uses a coordinate-based neural network to represent the field by mapping the spatial coordinates to the corresponding physical quantities, in our case the complex-valued refractive index values. We present DeCAF as the first NF-based IDT method that can learn a high-quality continuous representation of a RI volume from its intensity-only and limited-angle measurements. The representation in DeCAF is learned directly from the measurements of the test sample by using the IDT forward model, without any ground-truth RI maps. We qualitatively and quantitatively evaluate DeCAF on the simulated and experimental biological samples. Our results show that DeCAF can generate high-contrast and artifact-free RI maps and lead to up to 2.1 times reduction in MSE over existing methods.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 33 of its 72 references that are in the map. First posted on arXiv 27 Nov 2021.

Builds on

33 of 72 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  10. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  11. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  12. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
21 more
  1. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  2. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  3. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  4. 2017Image reconstruction by domain transform manifold learningcited by 231
  5. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 215
  6. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  7. 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
  8. 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
  9. 2019Plug and play methods for magnetic resonance imaging (long version)cited by 75
  10. 2021TermiNeRF: Ray Termination Prediction for Efficient Neural Renderingcited by 70
  11. 2021Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fieldscited by 69
  12. 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 49
  13. 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
  14. 2018Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalizationcited by 29
  15. 2018Deep speckle correlation: a deep learning approach towards scalable imaging through scattering mediacited by 23
  16. 2019SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priorscited by 16
  17. 2018Efficient and accurate inversion of multiple scattering with deep learningcited by 10
  18. 2019High-resolution 3D refractive index microscopy of multiple-scattering samples from intensity imagescited by 9
  19. 2020Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priorscited by 8
  20. 2018High-throughput intensity diffraction tomography with a computational microscopecited by 6
  21. 2021Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samplescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 14; 2024: 14; 2025: 13; 2026: 3.

48 papers.

Sort:

By area:

  1. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
  2. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 77
  3. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 67
  4. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  5. 2022Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomographycited by 31
  6. 2022DINER: Disorder-Invariant Implicit Neural Representationcited by 30
  7. 2023Disorder-invariant Implicit Neural Representationcited by 26
  8. 2023Equivariant plug-and-play image reconstructioncited by 26
  9. 2023IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRIcited by 22
  10. 2024Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisationcited by 12
  11. 2023RHINO: Regularizing the Hash-based Implicit Neural Representationcited by 9
  12. 2023Block Coordinate Plug-and-Play Methods for Blind Inverse Problemscited by 8
36 more
  1. 2023Self-Supervised Scalable Deep Compressed Sensingcited by 8
  2. 2023Single View Refractive Index Tomography with Neural Fieldscited by 8
  3. 2023Continuous 3D Myocardial Motion Tracking via Echocardiographycited by 5
  4. 2024Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Modelscited by 5
  5. 2024Enhancing Implicit Neural Representations via Symmetric Power Transformationcited by 4
  6. 2025Continuous Representation Methods, Theories, and Applications: An Overview and Perspectivescited by 4
  7. 2024Ray-driven Spectral CT Reconstruction Based on Neural Base-Material Fieldscited by 3
  8. 2023Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuitscited by 2
  9. 2023Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imagingcited by 2
  10. 2023Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Moviescited by 2
  11. 2023A Test-Time Learning Approach to Reparameterize the Geophysical Inverse Problem with a Convolutional Neural Networkcited by 2
  12. 2024Multiplane Quantitative Phase Imaging Using a Wavelength-Multiplexed Diffractive Optical Processorcited by 2
  13. 2024Towards the Spectral bias Alleviation by Normalizations in Coordinate Networkscited by 2
  14. 2025RSR-NF: Neural Field Regularization by Static Restoration Priors for Dynamic Imagingcited by 2
  15. 2025Towards Understanding the Benefits of Neural Network Parameterizations in Geophysical Inversions: A Study With Neural Fieldscited by 2
  16. 2025V2V3D: View-to-View Denoised 3D Reconstruction for Light-Field Microscopycited by 2
  17. 2025Plug-and-Play Posterior Sampling for Blind Inverse Problemscited by 2
  18. 2022Dual-Cycle: Self-Supervised Dual-View Fluorescence Microscopy Image Reconstruction using CycleGANcited by 1
  19. 2023High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fieldscited by 1
  20. 2024Learned 3D volumetric recovery of clouds and its uncertainty for climate analysiscited by 1
  21. 2024Enhancing Dynamic CT Image Reconstruction with Neural Fields and Optical Flowcited by 1
  22. 2024Neural Poisson Solver: A Universal and Continuous Framework for Natural Signal Blendingcited by 1
  23. 2024PNR: Physics-informed Neural Representation for high-resolution LFM reconstructioncited by 1
  24. 2024Single-shot reconstruction of three-dimensional morphology of biological cells in digital holographic microscopy using a physics-driven neural networkcited by 1
  25. 2025Neural Inverse Scattering with Score-based Regularizationcited by 1
  26. 2025Learning neural representations for X-ray ptychography reconstruction with unknown probescited by 1
  27. 2025Self-supervised Deep Unrolled Model with Implicit Neural Representation Regularization for Accelerating MRI Reconstructioncited by 1
  28. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1
  29. 2024Efficient and accurate neural field reconstruction using resistive memorycited by 0
  30. 2024Implicitly Learned Neural Phase Functions for Basis-Free Point Spread Function Engineeringcited by 0
  31. 2025Herglotz-NET: Implicit Neural Representation of Spherical Data with Harmonic Positional Encodingcited by 0
  32. 2025Low-Rank Augmented Implicit Neural Representation for Unsupervised High-Dimensional Quantitative MRI Reconstructioncited by 0
  33. 2025Accelerating multiparametric quantitative MRI using self-supervised scan-specific implicit neural representation with model reinforcementcited by 0
  34. 2025μNeuFMT: Optical-Property-Adaptive Fluorescence Molecular Tomography via Implicit Neural Representationcited by 0
  35. 2026ScoreField: Neural Inverse Scattering with Score-Based Generative Priorscited by 0
  36. 2026Implicit Neural Speckle Denoisingcited by 0