# Deep Phase Decoder: Self-calibrating phase microscopy with an untrained deep neural network

arXiv: https://arxiv.org/abs/2001.09803 · HTML: https://mlsanity.com/paper/2001.09803/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2020.

## Built on by (most cited first, 24 of 24)

- [Theoretical Perspectives on Deep Learning Methods in Inverse Problems](https://mlsanity.com/paper/2206.14373/) (2022)
- [On the use of deep learning for phase recovery](https://mlsanity.com/paper/2308.00942/) (2023)
- [Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement](https://mlsanity.com/paper/2105.08040/) (2021)
- [Self-Validation: Early Stopping for Single-Instance Deep Generative Priors](https://mlsanity.com/paper/2110.12271/) (2021)
- [Self-supervised learning of hologram reconstruction using physics consistency](https://mlsanity.com/paper/2209.08288/) (2022)
- [Untrained networks for compressive lensless photography](https://mlsanity.com/paper/2103.07609/) (2021)
- [TurbuGAN: An Adversarial Learning Approach to Spatially-Varying Multiframe Blind Deconvolution with Applications to Imaging Through Turbulence](https://mlsanity.com/paper/2203.06764/) (2022)
- [Blind Image Deblurring with Unknown Kernel Size and Substantial Noise](https://mlsanity.com/paper/2208.09483/) (2022)
- [Block Coordinate Plug-and-Play Methods for Blind Inverse Problems](https://mlsanity.com/paper/2305.12672/) (2023)
- [Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network](https://mlsanity.com/paper/2201.11333/) (2022)
- [Phase Retrieval using Single-Instance Deep Generative Prior](https://mlsanity.com/paper/2106.04812/) (2021)
- [Training Adaptive Reconstruction Networks for Blind Inverse Problems](https://mlsanity.com/paper/2202.11342/) (2022)
- [Differentiable model-based adaptive optics for two-photon microscopy](https://mlsanity.com/paper/2104.14308/) (2021)
- [Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits](https://mlsanity.com/paper/2304.04597/) (2023)
- [Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging](https://mlsanity.com/paper/2307.06207/) (2023)
- [Fast and Robust Phase Retrieval via Deep Expectation-Consistent Approximation](https://mlsanity.com/paper/2407.09687/) (2024)
- [Untrained, physics-informed neural networks for structured illumination microscopy](https://mlsanity.com/paper/2207.07705/) (2022)
- [MetaDIP: Accelerating Deep Image Prior with Meta Learning](https://mlsanity.com/paper/2209.08452/) (2022)
- [Low-light phase retrieval with implicit generative priors](https://mlsanity.com/paper/2402.17745/) (2024)
- [Untrained neural network embedded Fourier phase retrieval from few measurements](https://mlsanity.com/paper/2307.08717/) (2023)
- [Physics-driven generative adversarial networks empower single-pixel infrared hyperspectral imaging](https://mlsanity.com/paper/2311.13626/) (2023)
- [ConVRT: Consistent Video Restoration Through Turbulence with Test-time Optimization of Neural Video Representations](https://mlsanity.com/paper/2312.04679/) (2023)
- [Diffusion-driven lensless fiber endomicroscopic quantitative phase imaging towards digital pathology](https://mlsanity.com/paper/2407.18456/) (2024)
- [Breaking the Weak Recovery Limit in Random Phase Retrieval with Learned Regularizers](https://mlsanity.com/paper/2509.15026/) (2025)

## Abstract (arXiv)

Deep neural networks have emerged as effective tools for computational imaging including quantitative phase microscopy of transparent samples. To reconstruct phase from intensity, current approaches rely on supervised learning with training examples; consequently, their performance is sensitive to a match of training and imaging settings. Here we propose a new approach to phase microscopy by using an untrained deep neural network for measurement formation, encapsulating the image prior and imaging physics. Our approach does not require any training data and simultaneously reconstructs the sought phase and pupil-plane aberrations by fitting the weights of the network to the captured images. To demonstrate experimentally, we reconstruct quantitative phase from through-focus images blindly (i.e. no explicit knowledge of the aberrations).