The reviewed record of science sign in
Pith

arxiv: 2606.28431 · v1 · pith:2G7P3ENR · submitted 2026-06-26 · eess.IV · cs.CV· cs.LG· physics.optics

A Zero-Shot Deep Image Prior Framework for Denoising and Deconvolution in Fluorescence Microscopy

Xiangyu Qian , Jing Liu , Yunqing Tang , Luru Dai , Qiushi Li This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-06-30 01:34 UTCgrok-4.3pith:2G7P3ENRrecord.jsonopen to challenge →

classification eess.IV cs.CVcs.LGphysics.optics
keywords zero-shot deep image priorfluorescence microscopyimage denoisingdeconvolutionRichardson-Lucy guidanceimage restorationBioSR dataset
0
0 comments X

The pith

SDIP restores fluorescence microscopy images zero-shot by sequential autoencoding denoising followed by Richardson-Lucy guided deconvolution.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces SDIP as a zero-shot framework that restores fluorescence microscopy images degraded by noise and blur without any paired training data. It first applies an aSeqDIP module that suppresses noise through sequential autoencoding regularization while keeping fine structures. After a wavelet-based background correction step, the RLG-DIP module then performs deconvolution by incorporating the Richardson-Lucy result as a guidance prior that combines the physical imaging model with DIP's implicit prior. Experiments across multiple cellular structures on the BioSR dataset show gains in signal-to-noise ratio and resolution along with better visual quality on most structures.

Core claim

The central claim is that the RLG-DIP module stabilizes the ill-posed deconvolution by integrating the Richardson-Lucy deconvolution result as a physically consistent guidance prior into the DIP optimization, and that this sequential pipeline with aSeqDIP yields improved SNR and resolution when no external training data are available.

What carries the argument

RLG-DIP module, which uses the Richardson-Lucy deconvolution result as a physically consistent guidance prior integrated into the DIP optimization to stabilize the process.

If this is right

  • The sequential denoising-then-deconvolution pipeline improves both signal-to-noise ratio and resolution on the BioSR dataset across multiple cellular structures.
  • Superior visual quality and quantitative performance are achieved on most evaluated structures without requiring large-scale paired training datasets.
  • The framework integrates the imaging model directly with the implicit prior of DIP to reduce artifacts in deconvolution.
  • The approach may supply useful insights for designing physically guided DIP methods for other inverse problems in imaging.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same guidance-prior strategy could be tested on other microscopy modalities that have known forward models but lack paired data.
  • Performance on real experimental acquisitions with unknown ground truth would provide an additional check beyond the BioSR benchmark.
  • Extending the wavelet correction or the sequential regularization steps might further reduce background artifacts in low-signal regimes.

Load-bearing premise

The Richardson-Lucy deconvolution result supplies a physically consistent guidance prior that stabilizes the ill-posed deconvolution process when integrated into the DIP optimization.

What would settle it

Quantitative comparison on the BioSR dataset showing that SDIP fails to improve SNR or resolution relative to other zero-shot DIP baselines on the tested cellular structures would falsify the performance claim.

Figures

Figures reproduced from arXiv: 2606.28431 by Jing Liu, Luru Dai, Qiushi Li, Xiangyu Qian, Yunqing Tang.

Figure 1
Figure 1. Figure 1: The proposed SDIP zero-shot framework for fluorescence microscopy image processing. (a) Stage-wise denoising and deconvolution pipeline for [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Representative results of the aSeqDIP denoising module on samples with different cellular structures.(a–d) Denoising results on four typical subcellular [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of workflows and performance of different deconvolution DIP methods. (a) Schematic of three deconvolution DIP workflows. (b) [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Comparison of results by different deconvolution methods on representative cellular structure samples. The figure compares the restoration performance [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Stage-wise enhancement results of the proposed full-flow SDIP method on samples with CCPs (a) and ER (b). The figure presents the visualization [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Single-image training curves and deconvolution results of SDIP versus ZS-DeconvNet on the BioSR dataset.(a)CCPs structure, (b) ER structure. Each [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
read the original abstract

Fluorescence microscopy images are degraded by noise and diffraction-induced blur, which compromise structural fidelity and limit quantitative analysis. Supervised deep learning methods achieve impressive restoration performance but require large-scale paired datasets that are difficult to obtain in practice. To address this issue, we propose SDIP, a zero-shot deep image prior (DIP) framework that sequentially performs denoising and deconvolution without external training data. An aSeqDIP-based module first suppresses noise while preserving fine structures through sequential autoencoding regularization. In the deconvolution stage, a wavelet-based background correction step is incorporated before the proposed RLG-DIP module performs artifact-reduced deconvolution. RLG-DIP uses the Richardson-Lucy deconvolution result as a physically consistent guidance prior, integrating the imaging model with the implicit prior of DIP to stabilize the ill-posed deconvolution process. Experiments on the BioSR dataset across multiple cellular structures demonstrate that SDIP improves both signal-to-noise ratio and resolution, achieving superior visual quality and improved quantitative performance on most evaluated structures. The proposed framework may also provide useful insights for designing physically guided DIP methods for other inverse problems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper proposes SDIP, a zero-shot deep image prior (DIP) framework for sequential denoising and deconvolution of fluorescence microscopy images. It introduces an aSeqDIP module that uses sequential autoencoding regularization for noise suppression, followed by a wavelet-based background correction and an RLG-DIP module that incorporates the Richardson-Lucy (RL) deconvolution result as a physically consistent guidance prior to stabilize the ill-posed deconvolution. Experiments on the BioSR dataset across multiple cellular structures are reported to show improvements in SNR and resolution, with superior visual quality and quantitative performance on most structures.

Significance. If the performance claims hold with proper validation, the zero-shot nature of the method would be valuable for fluorescence microscopy applications where paired training data are scarce. The explicit integration of a physical imaging model (via RL) into the DIP optimization could offer a template for other inverse problems. However, the current manuscript provides no numerical metrics, baseline comparisons, error bars, or ablation results, so the significance cannot be assessed from the given text.

major comments (3)
  1. [RLG-DIP module description] The central claim that RLG-DIP stabilizes the ill-posed deconvolution by using the RL result as a physically consistent guidance prior (abstract and method description) is load-bearing, yet no ablation is presented that isolates the contribution of the RL guidance term (e.g., RLG-DIP vs. plain DIP or vs. DIP with a different prior). Without such isolation, performance gains cannot be attributed to the claimed stabilization mechanism.
  2. [Experiments on BioSR] The evaluation asserts superior SNR/resolution and quantitative performance on BioSR across cellular structures (abstract), but supplies no numerical values, baseline comparisons (e.g., to standard DIP, supervised methods, or RL alone), error bars, or statistical tests. This absence makes it impossible to verify the claim of improvement on “most evaluated structures.”
  3. [RLG-DIP module description] Richardson-Lucy iteration is known to amplify Poisson noise and produce ringing on low-SNR fluorescence data; the manuscript does not analyze the fidelity of the RL output before it is fed as guidance, nor does it describe how the guidance term is weighted inside the DIP loss function.
minor comments (2)
  1. [Abstract] The abstract states results but contains no quantitative metrics or figure references; the experiments section should include a table of SNR/PSNR/SSIM values and resolution metrics with standard deviations.
  2. [Method] Notation for the sequential autoencoding regularization in aSeqDIP and the precise form of the guidance loss in RLG-DIP should be defined with equations.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback on our manuscript. We appreciate the opportunity to clarify and strengthen our presentation of the SDIP framework. Below, we provide point-by-point responses to the major comments.

read point-by-point responses

  1. Referee: The central claim that RLG-DIP stabilizes the ill-posed deconvolution by using the RL result as a physically consistent guidance prior (abstract and method description) is load-bearing, yet no ablation is presented that isolates the contribution of the RL guidance term (e.g., RLG-DIP vs. plain DIP or vs. DIP with a different prior). Without such isolation, performance gains cannot be attributed to the claimed stabilization mechanism.

    Authors: We agree that an ablation isolating the RL guidance term is necessary to substantiate the stabilization claim. In the revised manuscript we will add an ablation study comparing RLG-DIP against plain DIP and against DIP using alternative priors, with quantitative metrics to attribute performance differences to the RL guidance. revision: yes

  2. Referee: The evaluation asserts superior SNR/resolution and quantitative performance on BioSR across cellular structures (abstract), but supplies no numerical values, baseline comparisons (e.g., to standard DIP, supervised methods, or RL alone), error bars, or statistical tests. This absence makes it impossible to verify the claim of improvement on “most evaluated structures.”

    Authors: The referee correctly notes the absence of explicit numerical tables, error bars, and statistical tests in the current text. We will revise the experiments section to include full numerical results, direct comparisons to standard DIP, RL alone, and relevant supervised baselines, together with error bars and statistical tests supporting the reported improvements on most structures. revision: yes

  3. Referee: Richardson-Lucy iteration is known to amplify Poisson noise and produce ringing on low-SNR fluorescence data; the manuscript does not analyze the fidelity of the RL output before it is fed as guidance, nor does it describe how the guidance term is weighted inside the DIP loss function.

    Authors: We will add an analysis of RL-output fidelity, including visual and quantitative evaluation of noise amplification and ringing on the BioSR images. We will also provide the precise mathematical form of the guidance term within the DIP loss, including the weighting coefficient and the procedure used to select it. revision: yes

Circularity Check

0 steps flagged

No significant circularity; framework is experimental and self-contained against external benchmarks.

full rationale

The paper introduces SDIP as a zero-shot method combining sequential DIP denoising (aSeqDIP) with RLG-DIP that incorporates Richardson-Lucy output as guidance prior, followed by wavelet correction. All performance claims rest on empirical results on the external BioSR dataset across cellular structures, with quantitative metrics for SNR and resolution. No derivation chain, fitted parameters renamed as predictions, or self-citation load-bearing steps are present in the provided text. The central stabilization claim is justified by the integration of the imaging model with DIP's implicit prior, but this is presented as a design choice validated experimentally rather than by mathematical reduction to inputs. No equations or self-referential definitions appear.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no explicit free parameters, axioms, or invented entities are stated beyond the high-level algorithmic description.

pith-pipeline@v0.9.1-grok · 5745 in / 983 out tokens · 37460 ms · 2026-06-30T01:34:30.478050+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

37 extracted references · 8 canonical work pages · 1 internal anchor

  1. [1]

    Super-resolution microscopy demystified,

    L. Schermelleh, A. Ferrand, T. Huser, C. Eggeling, M. Sauer, O. Biehlmaier, and G. P. Drummen, “Super-resolution microscopy demystified,”Nature cell biology, vol. 21, no. 1, pp. 72–84, 2019

    2019

  2. [2]

    A poisson-gaussian denoising dataset with real fluorescence microscopy images,

    Y . Zhang, Y . Zhu, E. Nichols, Q. Wang, S. Zhang, C. Smith, and S. Howard, “A poisson-gaussian denoising dataset with real fluorescence microscopy images,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11 710–11 718

    2019

  3. [3]

    Bertero, P

    M. Bertero, P. Boccacci, and C. De MoI,Introduction to Inverse Problems in Imaging, 2nd ed. Boca Raton: CRC Press, Oct. 2021. [Online]. Available: https://www.taylorfrancis.com/books/9781003032755

    work page arXiv 2021

  4. [4]

    Computational super-resolution: An odyssey in harnessing priors to enhance optical microscopy resolution,

    W. Tian, R. Chen, and L. Chen, “Computational super-resolution: An odyssey in harnessing priors to enhance optical microscopy resolution,”Analytical Chemistry, vol. 97, no. 9, pp. 4763–4792, 2025

    2025

  5. [5]

    Bayesian-based iterative method of image restoration,

    W. H. Richardson, “Bayesian-based iterative method of image restoration,”Journal of the optical society of America, vol. 62, no. 1, pp. 55–59, 1972

    1972

  6. [6]

    An iterative technique for the rectification of observed distributions,

    L. B. Lucy, “An iterative technique for the rectification of observed distributions,”Astronomical Journal, Vol. 79, p. 745 (1974), vol. 79, p. 745, 1974

    1974

  7. [7]

    Evaluation and development of deep neural networks for image super-resolution in optical microscopy,

    C. Qiao, D. Li, Y . Guo, C. Liu, T. Jiang, Q. Dai, and D. Li, “Evaluation and development of deep neural networks for image super-resolution in optical microscopy,”Nature methods, vol. 18, no. 2, pp. 194–202, 2021

    2021

  8. [8]

    Incorporating the image formation process into deep learning improves network performance,

    Y . Li, Y . Su, M. Guo, X. Han, J. Liu, H. D. Vishwasrao, X. Li, R. Christensen, T. Sengupta, M. W. Moyleet al., “Incorporating the image formation process into deep learning improves network performance,”Nature Methods, vol. 19, no. 11, pp. 1427–1437, 2022

    2022

  9. [9]

    Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes,

    C. Qiao, D. Li, Y . Liu, S. Zhang, K. Liu, C. Liu, Y . Guo, T. Jiang, C. Fang, N. Liet al., “Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes,”Nature biotechnology, vol. 41, no. 3, pp. 367–377, 2023

    2023

  10. [10]

    Noise2Noise: Learning Image Restoration without Clean Data

    J. Lehtinen, J. Munkberg, J. Hasselgren, S. Laine, T. Karras, M. Aittala, and T. Aila, “Noise2noise: Learning image restoration without clean data,” arXiv preprint arXiv:1803.04189, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  11. [11]

    Noise2void-learning denoising from single noisy images,

    A. Krull, T.-O. Buchholz, and F. Jug, “Noise2void-learning denoising from single noisy images,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 2129–2137

    2019

  12. [12]

    Noise2self: Blind denoising by self-supervision,

    J. Batson and L. Royer, “Noise2self: Blind denoising by self-supervision,” inInternational conference on machine learning. PMLR, 2019, pp. 524–533

    2019

  13. [13]

    Self2self with dropout: Learning self-supervised denoising from single image,

    Y . Quan, M. Chen, T. Pang, and H. Ji, “Self2self with dropout: Learning self-supervised denoising from single image,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 1890–1898

    2020

  14. [14]

    A fast blind zero-shot denoiser,

    J. Lequyer, R. Philip, A. Sharma, W.-H. Hsu, and L. Pelletier, “A fast blind zero-shot denoiser,”Nature Machine Intelligence, vol. 4, no. 11, pp. 953–963, 2022

    2022

  15. [15]

    Self-supervised denoising for multimodal structured illumination microscopy enables long-term super-resolution live-cell imaging,

    X. Chen, C. Qiao, T. Jiang, J. Liu, Q. Meng, Y . Zeng, H. Chen, H. Qiao, D. Li, and J. Wu, “Self-supervised denoising for multimodal structured illumination microscopy enables long-term super-resolution live-cell imaging,”PhotoniX, vol. 5, no. 1, p. 4, 2024

    2024

  16. [16]

    Zero-shot learning enables instant denoising and super-resolution in optical fluorescence microscopy,

    C. Qiao, Y . Zeng, Q. Meng, X. Chen, H. Chen, T. Jiang, R. Wei, J. Guo, W. Fu, H. Luet al., “Zero-shot learning enables instant denoising and super-resolution in optical fluorescence microscopy,”Nature communications, vol. 15, no. 1, p. 4180, 2024

    2024

  17. [17]

    Self-inspired learning for denoising live-cell super-resolution microscopy,

    L. Qu, S. Zhao, Y . Huang, X. Ye, K. Wang, Y . Liu, X. Liu, H. Mao, G. Hu, W. Chenet al., “Self-inspired learning for denoising live-cell super-resolution microscopy,”Nature Methods, vol. 21, no. 10, pp. 1895–1908, 2024

    1908

  18. [18]

    Deep image prior,

    D. Ulyanov, A. Vedaldi, and V . Lempitsky, “Deep image prior,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 9446–9454

    2018

  19. [19]

    Image denoising by sparse 3-d transform-domain collaborative filtering,

    K. Dabov, A. Foi, V . Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-d transform-domain collaborative filtering,”IEEE Transactions on image processing, vol. 16, no. 8, pp. 2080–2095, 2007

    2080

  20. [20]

    Fast and accurate sCMOS noise correction for fluorescence microscopy,

    B. Mandracchia, X. Hua, C. Guo, J. Son, T. Urner, and S. Jia, “Fast and accurate sCMOS noise correction for fluorescence microscopy,”Nature Communications, vol. 11, no. 1, p. 94, Jan. 2020. [Online]. Available: https://doi.org/10.1038/s41467-019-13841-8 13 Fig. 6. Single-image training curves and deconvolution results of SDIP versus ZS-DeconvNet on the Bi...

    work page doi:10.1038/s41467-019-13841-8 2020

  21. [21]

    Content-aware image 14 restoration: pushing the limits of fluorescence microscopy,

    M. Weigert, U. Schmidt, T. Boothe, A. M ¨uller, A. Dibrov, A. Jain, B. Wilhelm, D. Schmidt, C. Broaddus, S. Culleyet al., “Content-aware image 14 restoration: pushing the limits of fluorescence microscopy,”Nature methods, vol. 15, no. 12, pp. 1090–1097, 2018

    2018

  22. [22]

    Sparse deconvolution improves the resolution of live-cell super-resolution fluorescence microscopy,

    W. Zhao, S. Zhao, L. Li, X. Huang, S. Xing, Y . Zhang, G. Qiu, Z. Han, Y . Shang, D.-e. Sunet al., “Sparse deconvolution improves the resolution of live-cell super-resolution fluorescence microscopy,”Nature biotechnology, vol. 40, no. 4, pp. 606–617, 2022

    2022

  23. [23]

    Fast, long-term, super-resolution imaging with Hessian structured illumination microscopy,

    X. Huang, J. Fan, L. Li, H. Liu, R. Wu, Y . Wu, L. Wei, H. Mao, A. Lal, P. Xi, L. Tang, Y . Zhang, Y . Liu, S. Tan, and L. Chen, “Fast, long-term, super-resolution imaging with Hessian structured illumination microscopy,”Nature Biotechnology, vol. 36, no. 5, pp. 451–459, May 2018. [Online]. Available: https://www.nature.com/articles/nbt.4115

    2018

  24. [24]

    Nonlinear total variation based noise removal algorithms,

    L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,”Physica D: nonlinear phenomena, vol. 60, no. 1-4, pp. 259–268, 1992

    1992

  25. [25]

    Deep learning enables cross-modality super-resolution in fluorescence microscopy,

    H. Wang, Y . Rivenson, Y . Jin, Z. Wei, R. Gao, H. G ¨unaydın, L. A. Bentolila, C. Kural, and A. Ozcan, “Deep learning enables cross-modality super-resolution in fluorescence microscopy,”Nature Methods, vol. 16, no. 1, pp. 103–110, Jan. 2019. [Online]. Available: http://www.nature.com/articles/s41592-018-0239-0

    2019

  26. [26]

    A neural network for long-term super-resolution imaging of live cells with reliable confidence quantification,

    C. Qiao, S. Liu, Y . Wang, W. Xu, X. Geng, T. Jiang, J. Zhang, Q. Meng, H. Qiao, D. Li, and Q. Dai, “A neural network for long-term super-resolution imaging of live cells with reliable confidence quantification,”Nature Biotechnology, Jan. 2025. [Online]. Available: https://doi.org/10.1038/s41587-025-02553-8

    work page doi:10.1038/s41587-025-02553-8 2025

  27. [27]

    Spatial redundancy transformer for self-supervised fluorescence image denoising,

    X. Li, X. Hu, X. Chen, J. Fan, Z. Zhao, J. Wu, H. Wang, and Q. Dai, “Spatial redundancy transformer for self-supervised fluorescence image denoising,”Nature Computational Science, vol. 3, no. 12, pp. 1067–1080, Dec. 2023. [Online]. Available: https://doi.org/10.1038/s43588-023-00568-2

    work page doi:10.1038/s43588-023-00568-2 2023

  28. [28]

    Real-time self-supervised denoising for high-speed fluorescence neural imaging,

    Y . Wang, Y . Gu, J. Wang, A. Xuan, C. Kong, W.-Q. Fang, D. Li, D. Zhu, F. Ding, and B. Dong, “Real-time self-supervised denoising for high-speed fluorescence neural imaging,”Nature Communications, vol. 16, no. 1, p. 9396, Oct. 2025. [Online]. Available: https://doi.org/10.1038/s41467-025-64681-8

    work page doi:10.1038/s41467-025-64681-8 2025

  29. [29]

    Image restoration using total variation regularized deep image prior,

    J. Liu, Y . Sun, X. Xu, and U. S. Kamilov, “Image restoration using total variation regularized deep image prior,” inICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Ieee, 2019, pp. 7715–7719

    2019

  30. [30]

    A bayesian perspective on the deep image prior,

    Z. Cheng, M. Gadelha, S. Maji, and D. Sheldon, “A bayesian perspective on the deep image prior,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5443–5451

    2019

  31. [31]

    Deepred: Deep image prior powered by red,

    G. Mataev, P. Milanfar, and M. Elad, “Deepred: Deep image prior powered by red,” inProceedings of the IEEE/CVF international conference on computer vision workshops, 2019, pp. 0–0

    2019

  32. [32]

    Self-validation: Early stopping for single-instance deep generative priors,

    T. Li, Z. Zhuang, H. Liang, L. Peng, H. Wang, and J. Sun, “Self-validation: Early stopping for single-instance deep generative priors,”arXiv preprint arXiv:2110.12271, 2021

    work page arXiv 2021

  33. [33]

    Early stopping for deep image prior,

    H. Wang, T. Li, Z. Zhuang, T. Chen, H. Liang, and J. Sun, “Early stopping for deep image prior,”arXiv preprint arXiv:2112.06074, 2021

    work page arXiv 2021

  34. [34]

    Image reconstruction via autoencoding sequential deep image prior,

    I. R. Alkhouri, S. Liang, E. Bell, Q. Qu, R. Wang, and S. Ravishankar, “Image reconstruction via autoencoding sequential deep image prior,”Advances in Neural Information Processing Systems, vol. 37, pp. 18 988–19 012, 2024

    2024

  35. [35]

    SDIP: Self-reinforcement deep image prior framework for image processing,

    Z. Shu and Z. Pan, “SDIP: Self-reinforcement deep image prior framework for image processing,”Pattern Recognition, vol. 168, p. 111786, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0031320325004467

    2025

  36. [36]

    Surpassing the resolution limitation of structured illumination microscopy by an untrained neural network,

    Y . He, Y . Yao, Y . He, Z. Huang, F. Luo, C. Zhang, D. Qi, T. Jia, Z. Wang, Z. Sun, X. Yuan, and S. Zhang, “Surpassing the resolution limitation of structured illumination microscopy by an untrained neural network,”Biomedical Optics Express, vol. 14, no. 1, p. 106, Jan. 2023. [Online]. Available: https://opg.optica.org/abstract.cfm?URI=boe-14-1-106

    2023

  37. [37]

    Parameter-free image resolution estimation based on decorrelation analysis,

    A. Descloux, K. S. Grußmayer, and A. Radenovic, “Parameter-free image resolution estimation based on decorrelation analysis,”Nature methods, vol. 16, no. 9, pp. 918–924, 2019

    2019