English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper investigates the application of unsupervised learning methods forcomputed tomography (CT) reconstruction. To motivate our work, we reviewseveral existing priors, namely the truncated Gaussian prior, the $l_1$ prior,the total variation prior, and the deep image prior (DIP). We find that DIPoutperforms the other three priors in terms of representational capability andvisual performance. However, the performance of DIP deteriorates when thenumber of iterations exceeds a certain threshold due to overfitting. To addressthis issue, we propose a novel method (MCDIP-ADMM) based on Multi-Code DeepImage Prior and plug-and-play Alternative Direction Method of Multipliers.Specifically, MCDIP utilizes multiple latent codes to generate a series offeature maps at an intermediate layer within a generator model. These maps arethen composed with trainable weights, representing the complete image prior.Experimental results demonstrate the superior performance of the proposedMCDIP-ADMM compared to three existing competitors. In the case of parallel beamprojection with Gaussian noise, MCDIP-ADMM achieves an average improvement of4.3 dB over DIP, 1.7 dB over ADMM DIP-WTV, and 1.2 dB over PnP-DIP in terms ofPSNR. Similarly, for fan-beam projection with Poisson noise, MCDIP-ADMMachieves 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.

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