# MCDIP-ADMM: Overcoming Overfitting in DIP-based CT reconstruction

arXiv: https://arxiv.org/abs/2304.03895 · HTML: https://mlsanity.com/paper/2304.03895/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 8 Apr 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications](https://mlsanity.com/paper/1605.01710/) (2016)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [DeepRED: Deep Image Prior Powered by RED](https://mlsanity.com/paper/1903.10176/) (2019)
- [A Bayesian Perspective on the Deep Image Prior](https://mlsanity.com/paper/1904.07457/) (2019)
- [TorchRadon: Fast Differentiable Routines for Computed Tomography](https://mlsanity.com/paper/2009.14788/) (2020)
- [Early Stopping for Deep Image Prior](https://mlsanity.com/paper/2112.06074/) (2021)
- [On Measuring and Controlling the Spectral Bias of the Deep Image Prior](https://mlsanity.com/paper/2107.01125/) (2021)
- [Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization](https://mlsanity.com/paper/2006.08857/) (2020)
- [Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery](https://mlsanity.com/paper/2109.11154/) (2021)
- [Deep Plug-and-Play Prior for Hyperspectral Image Restoration](https://mlsanity.com/paper/2209.08240/) (2022)
- [Conditional Invertible Neural Networks for Medical Imaging](https://mlsanity.com/paper/2110.14520/) (2021)
- [Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting](https://mlsanity.com/paper/2011.01748/) (2020)
- [Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM](https://mlsanity.com/paper/2009.11380/) (2020)
- [Physics Embedded Machine Learning for Electromagnetic Data Imaging](https://mlsanity.com/paper/2207.12607/) (2022)
- [SVD-DIP: Overcoming the Overfitting Problem in DIP-based CT Reconstruction](https://mlsanity.com/paper/2303.15748/) (2023)

## Built on by (most cited first, 1 of 1)

- [Bayesian imaging inverse problem with SA-Roundtrip prior via HMC-pCN sampler](https://mlsanity.com/paper/2310.17817/) (2023)

## Abstract (arXiv)

This paper investigates the application of unsupervised learning methods for computed tomography (CT) reconstruction. To motivate our work, we review several existing priors, namely the truncated Gaussian prior, the l1 prior, the total variation prior, and the deep image prior (DIP). We find that DIP outperforms the other three priors in terms of representational capability and visual performance. However, the performance of DIP deteriorates when the number of iterations exceeds a certain threshold due to overfitting. To address this issue, we propose a novel method (MCDIP-ADMM) based on Multi-Code Deep Image Prior and plug-and-play Alternative Direction Method of Multipliers. Specifically, MCDIP utilizes multiple latent codes to generate a series of feature maps at an intermediate layer within a generator model. These maps are then composed with trainable weights, representing the complete image prior. Experimental results demonstrate the superior performance of the proposed MCDIP-ADMM compared to three existing competitors. In the case of parallel beam projection with Gaussian noise, MCDIP-ADMM achieves an average improvement of 4.3 dB over DIP, 1.7 dB over ADMM DIP-WTV, and 1.2 dB over PnP-DIP in terms of PSNR. Similarly, for fan-beam projection with Poisson noise, MCDIP-ADMM achieves an average improvement of 3.09 dB over DIP, 1.86 dB over ADMM DIP-WTV, and 0.84 dB over PnP-DIP in terms of PSNR.