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 present neural radiance fields for rendering and temporal (4D)reconstruction of humans in motion (H-NeRF), as captured by a sparse set ofcameras or even from a monocular video. Our approach combines ideas from neuralscene representation, novel-view synthesis, and implicit statistical geometrichuman representations, coupled using novel loss functions. Instead of learninga radiance field with a uniform occupancy prior, we constrain it by astructured implicit human body model, represented using signed distancefunctions. This allows us to robustly fuse information from sparse views andgeneralize well beyond the poses or views observed in training. Moreover, weapply geometric constraints to co-learn the structure of the observed subject-- including both body and clothing -- and to regularize the radiance field togeometrically plausible solutions. Extensive experiments on multiple datasetsdemonstrate the robustness and the accuracy of our approach, its generalizationcapabilities significantly outside a small training set of poses and views, andstatistical extrapolation beyond the observed shape.

H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion