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

We introduce MotioNet, a deep neural network that directly reconstructs themotion of a 3D human skeleton from monocular video.While previous methods relyon either rigging or inverse kinematics (IK) to associate a consistent skeletonwith temporally coherent joint rotations, our method is the first data-drivenapproach that directly outputs a kinematic skeleton, which is a complete,commonly used, motion representation. At the crux of our approach lies a deepneural network with embedded kinematic priors, which decomposes sequences of 2Djoint positions into two separate attributes: a single, symmetric, skeleton,encoded by bone lengths, and a sequence of 3D joint rotations associated withglobal root positions and foot contact labels. These attributes are fed into anintegrated forward kinematics (FK) layer that outputs 3D positions, which arecompared to a ground truth. In addition, an adversarial loss is applied to thevelocities of the recovered rotations, to ensure that they lie on the manifoldof natural joint rotations. The key advantage of our approach is that it learnsto infer natural joint rotations directly from the training data, rather thanassuming an underlying model, or inferring them from joint positions using adata-agnostic IK solver. We show that enforcing a single consistent skeletonalong with temporally coherent joint rotations constrains the solution space,leading to a more robust handling of self-occlusions and depth ambiguities.

MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency