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

Unsupervised methods for reconstructing structures face significantchallenges in capturing the geometric details with consistent structures amongdiverse shapes of the same category. To address this issue, we present a novelunsupervised structural reconstruction method, named DPF-Net, based on a newDeformable Primitive Field (DPF) representation, which allows for high-qualityshape reconstruction using parameterized geometric primitives. We design atwo-stage shape reconstruction pipeline which consists of a primitivegeneration module and a primitive deformation module to approximate the targetshape of each part progressively. The primitive generation module estimates theexplicit orientation, position, and size parameters of parameterized geometricprimitives, while the primitive deformation module predicts a dense deformationfield based on a parameterized primitive field to recover shape details. Thestrong shape prior encoded in parameterized geometric primitives enables ourDPF-Net to extract high-level structures and recover fine-grained shape detailsconsistently. The experimental results on three categories of objects indiverse shapes demonstrate the effectiveness and generalization ability of ourDPF-Net on structural reconstruction and shape segmentation.

DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects