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

Creating controllable, photorealistic, and geometrically detailed digitaldoubles of real humans solely from video data is a key challenge in ComputerGraphics and Vision, especially when real-time performance is required. Recentmethods attach a neural radiance field (NeRF) to an articulated structure,e.g., a body model or a skeleton, to map points into a pose canonical spacewhile conditioning the NeRF on the skeletal pose. These approaches typicallyparameterize the neural field with a multi-layer perceptron (MLP) leading to aslow runtime. To address this drawback, we propose TriHuman a novelhuman-tailored, deformable, and efficient tri-plane representation, whichachieves real-time performance, state-of-the-art pose-controllable geometrysynthesis as well as photorealistic rendering quality. At the core, wenon-rigidly warp global ray samples into our undeformed tri-plane texturespace, which effectively addresses the problem of global points being mapped tothe same tri-plane locations. We then show how such a tri-plane featurerepresentation can be conditioned on the skeletal motion to account for dynamicappearance and geometry changes. Our results demonstrate a clear step towardshigher quality in terms of geometry and appearance modeling of humans as wellas runtime performance.

TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis