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

Acquisition and creation of digital human avatars is an important problemwith applications to virtual telepresence, gaming, and human modeling. Mostcontemporary approaches for avatar generation can be viewed either as 3D-basedmethods, which use multi-view data to learn a 3D representation with appearance(such as a mesh, implicit surface, or volume), or 2D-based methods which learnphoto-realistic renderings of avatars but lack accurate 3D representations. Inthis work, we present, DRaCoN, a framework for learning full-body volumetricavatars which exploits the advantages of both the 2D and 3D neural renderingtechniques. It consists of a Differentiable Rasterization module, DiffRas, thatsynthesizes a low-resolution version of the target image along with additionallatent features guided by a parametric body model. The output of DiffRas isthen used as conditioning to our conditional neural 3D representation module(c-NeRF) which generates the final high-res image along with body geometryusing volumetric rendering. While DiffRas helps in obtaining photo-realisticimage quality, c-NeRF, which employs signed distance fields (SDF) for 3Drepresentations, helps to obtain fine 3D geometric details. Experiments on thechallenging ZJU-MoCap and Human3.6M datasets indicate that DRaCoN outperformsstate-of-the-art methods both in terms of error metrics and visual quality.

DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars