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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Porous media are ubiquitous in both nature and engineering applications, thustheir modelling and understanding is of vital importance. In contrast to directacquisition of three-dimensional (3D) images of such medium, obtaining itssub-region (s) like two-dimensional (2D) images or several small areas could bemuch feasible. Therefore, reconstructing whole images from the limitedinformation is a primary technique in such cases. Specially, in practice thegiven data cannot generally be determined by users and may be incomplete orpartially informed, thus making existing reconstruction methods inaccurate oreven ineffective. To overcome this shortcoming, in this study we proposed adeep learning-based framework for reconstructing full image from its muchsmaller sub-area(s). Particularly, conditional generative adversarial network(CGAN) is utilized to learn the mapping between input (partial image) andoutput (full image). To preserve the reconstruction accuracy, two simple buteffective objective functions are proposed and then coupled with the other twofunctions to jointly constrain the training procedure. Due to the inherentessence of this ill-posed problem, a Gaussian noise is introduced for producingreconstruction diversity, thus allowing for providing multiple candidateoutputs. Extensively tested on a variety of porous materials and demonstratedby both visual inspection and quantitative comparison, the method is shown tobe accurate, stable yet fast ($\sim0.08s$ for a $128 \times 128$ imagereconstruction). We highlight that the proposed approach can be readilyextended, such as incorporating any user-define conditional data and anarbitrary number of object functions into reconstruction, and being coupledwith other reconstruction methods.

Accurate and Fast reconstruction of Porous Media from Extremely Limited Information Using Conditional Generative Adversarial Network