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

We tackle the problem of monocular 3D reconstruction of articulated objectslike humans and animals. We contribute DensePose 3D, a method that can learnsuch reconstructions in a weakly supervised fashion from 2D image annotationsonly. This is in stark contrast with previous deformable reconstruction methodsthat use parametric models such as SMPL pre-trained on a large dataset of 3Dobject scans. Because it does not require 3D scans, DensePose 3D can be usedfor learning a wide range of articulated categories such as different animalspecies. The method learns, in an end-to-end fashion, a soft partition of agiven category-specific 3D template mesh into rigid parts together with amonocular reconstruction network that predicts the part motions such that theyreproject correctly onto 2D DensePose-like surface annotations of the object.The decomposition of the object into parts is regularized by expressing partassignments as a combination of the smooth eigenfunctions of theLaplace-Beltrami operator. We show significant improvements compared tostate-of-the-art non-rigid structure-from-motion baselines on both syntheticand real data on categories of humans and animals.

DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension