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 propose a new method for learning a generalized animatable neural humanrepresentation from a sparse set of multi-view imagery of multiple persons. Thelearned representation can be used to synthesize novel view images of anarbitrary person from a sparse set of cameras, and further animate them withthe user's pose control. While existing methods can either generalize to newpersons or synthesize animations with user control, none of them can achieveboth at the same time. We attribute this accomplishment to the employment of a3D proxy for a shared multi-person human model, and further the warping of thespaces of different poses to a shared canonical pose space, in which we learn aneural field and predict the person- and pose-dependent deformations, as wellas appearance with the features extracted from input images. To cope with thecomplexity of the large variations in body shapes, poses, and clothingdeformations, we design our neural human model with disentangled geometry andappearance. Furthermore, we utilize the image features both at the spatialpoint and on the surface points of the 3D proxy for predicting person- andpose-dependent properties. Experiments show that our method significantlyoutperforms the state-of-the-arts on both tasks. The video and code areavailable at https://talegqz.github.io/neural_novel_actor.

Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors