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

Sparse-view CT is a promising strategy for reducing the radiation dose oftraditional CT scans, but reconstructing high-quality images from incompleteand noisy data is challenging. Recently, 3D Gaussian has been applied to modelcomplex natural scenes, demonstrating fast convergence and better rendering ofnovel views compared to implicit neural representations (INRs). Takinginspiration from the successful application of 3D Gaussians in natural scenemodeling and novel view synthesis, we investigate their potential forsparse-view CT reconstruction. We leverage prior information from thefiltered-backprojection reconstructed image to initialize the Gaussians; andupdate their parameters via comparing difference in the projection space.Performance is further enhanced by adaptive density control. Compared to INRs,3D Gaussians benefit more from prior information to explicitly bypass learningin void spaces and allocate the capacity efficiently, accelerating convergence.3D Gaussians also efficiently learn high-frequency details. Trained in aself-supervised manner, 3D Gaussians avoid the need for large-scale paireddata. Our experiments on the AAPM-Mayo dataset demonstrate that 3D Gaussianscan provide superior performance compared to INR-based methods. This work is inprogress, and the code will be publicly available.

Sparse-view CT Reconstruction with 3D Gaussian Volumetric Representation