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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

3D reconstruction from a single view image is a long-standing prob-lem incomputer vision. Various methods based on different shape representations(suchas point cloud or volumetric representations) have been proposed. However,the3D shape reconstruction with fine details and complex structures are stillchal-lenging and have not yet be solved. Thanks to the recent advance of thedeepshape representations, it becomes promising to learn the structure anddetail rep-resentation using deep neural networks. In this paper, we propose anovel methodcalled STD-Net to reconstruct the 3D models utilizing the meshrepresentationthat is well suitable for characterizing complex structure andgeometry details.To reconstruct complex 3D mesh models with fine details, ourmethod consists of(1) an auto-encoder network for recovering the structure ofan object with bound-ing box representation from a single image, (2) atopology-adaptive graph CNNfor updating vertex position for meshes of complextopology, and (3) an unifiedmesh deformation block that deforms the structuralboxes into structure-awaremeshed models. Experimental results on the imagesfrom ShapeNet show that ourproposed STD-Net has better performance than otherstate-of-the-art methods onreconstructing 3D objects with complex structuresand fine geometric details.

STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image