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

This paper proposes a novel and fast self-supervised solution for sparse-viewCBCT reconstruction (Cone Beam Computed Tomography) that requires no externaltraining data. Specifically, the desired attenuation coefficients arerepresented as a continuous function of 3D spatial coordinates, parameterizedby a fully-connected deep neural network. We synthesize projections discretelyand train the network by minimizing the error between real and synthesizedprojections. A learning-based encoder entailing hash coding is adopted to helpthe network capture high-frequency details. This encoder outperforms thecommonly used frequency-domain encoder in terms of having higher performanceand efficiency, because it exploits the smoothness and sparsity of humanorgans. Experiments have been conducted on both human organ and phantomdatasets. The proposed method achieves state-of-the-art accuracy and spendsreasonably short computation time.

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction