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

Human volumetric capture is a long-standing topic in computer vision andcomputer graphics. Although high-quality results can be achieved usingsophisticated off-line systems, real-time human volumetric capture of complexscenarios, especially using light-weight setups, remains challenging. In thispaper, we propose a human volumetric capture method that combines temporalvolumetric fusion and deep implicit functions. To achieve high-quality andtemporal-continuous reconstruction, we propose dynamic sliding fusion to fuseneighboring depth observations together with topology consistency. Moreover,for detailed and complete surface generation, we propose detail-preserving deepimplicit functions for RGBD input which can not only preserve the geometricdetails on the depth inputs but also generate more plausible texturing results.Results and experiments show that our method outperforms existing methods interms of view sparsity, generalization capacity, reconstruction quality, andrun-time efficiency.

Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors