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

Rendering photorealistic and dynamically moving human heads is crucial forensuring a pleasant and immersive experience in AR/VR and video conferencingapplications. However, existing methods often struggle to model challengingfacial regions (e.g., mouth interior, eyes, hair/beard), resulting inunrealistic and blurry results. In this paper, we propose {\fullname}({\name}), a method that adopts the neural point representation as well as theneural volume rendering process and discards the predefined connectivity andhard correspondence imposed by mesh-based approaches. Specifically, the neuralpoints are strategically constrained around the surface of the targetexpression via a high-resolution UV displacement map, achieving increasedmodeling capacity and more accurate control. We introduce three technicalinnovations to improve the rendering and training efficiency: a patch-wisedepth-guided (shading point) sampling strategy, a lightweight radiance decodingprocess, and a Grid-Error-Patch (GEP) ray sampling strategy during training. Bydesign, our {\name} is better equipped to handle topologically changing regionsand thin structures while also ensuring accurate expression control whenanimating avatars. Experiments conducted on three subjects from the Multifacedataset demonstrate the effectiveness of our designs, outperforming previousstate-of-the-art methods, especially in handling challenging facial regions.

Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatar