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

In this paper, we introduce 3D-GMNet, a deep neural network for 3D objectshape reconstruction from a single image. As the name suggests, 3D-GMNetrecovers 3D shape as a Gaussian mixture. In contrast to voxels, point clouds,or meshes, a Gaussian mixture representation provides an analytical expressionwith a small memory footprint while accurately representing the target 3Dshape. At the same time, it offers a number of additional advantages includinginstant pose estimation and controllable level-of-detail reconstruction, whilealso enabling interpretation as a point cloud, volume, and a mesh model. Wetrain 3D-GMNet end-to-end with single input images and corresponding 3D modelsby introducing two novel loss functions, a 3D Gaussian mixture loss and a 2Dmulti-view loss, which collectively enable accurate shape reconstruction askernel density estimation. We thoroughly evaluate the effectiveness of 3D-GMNetwith synthetic and real images of objects. The results show accuratereconstruction with a compact representation that also realizes novelapplications of single-image 3D reconstruction.

3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture