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 propose DoubleFusion, a new real-time system that combines volumetricdynamic reconstruction with data-driven template fitting to simultaneouslyreconstruct detailed geometry, non-rigid motion and the inner human body shapefrom a single depth camera. One of the key contributions of this method is adouble layer representation consisting of a complete parametric body shapeinside, and a gradually fused outer surface layer. A pre-defined node graph onthe body surface parameterizes the non-rigid deformations near the body, and afree-form dynamically changing graph parameterizes the outer surface layer farfrom the body, which allows more general reconstruction. We further propose ajoint motion tracking method based on the double layer representation to enablerobust and fast motion tracking performance. Moreover, the inner body shape isoptimized online and forced to fit inside the outer surface layer. Overall, ourmethod enables increasingly denoised, detailed and complete surfacereconstructions, fast motion tracking performance and plausible inner bodyshape reconstruction in real-time. In particular, experiments show improvedfast motion tracking and loop closure performance on more challengingscenarios.

DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor