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 introduce You Only Train Once (YOTO), a dynamic human generationframework, which performs free-viewpoint rendering of different humanidentities with distinct motions, via only one-time training from monocularvideos. Most prior works for the task require individualized optimization foreach input video that contains a distinct human identity, leading to asignificant amount of time and resources for the deployment, thereby impedingthe scalability and the overall application potential of the system. In thispaper, we tackle this problem by proposing a set of learnable identity codes toexpand the capability of the framework for multi-identity free-viewpointrendering, and an effective pose-conditioned code query mechanism to finelymodel the pose-dependent non-rigid motions. YOTO optimizes neural radiancefields (NeRF) by utilizing designed identity codes to condition the model forlearning various canonical T-pose appearances in a single shared volumetricrepresentation. Besides, our joint learning of multiple identities within aunified model incidentally enables flexible motion transfer in high-qualityphoto-realistic renderings for all learned appearances. This capability expandsits potential use in important applications, including Virtual Reality. Wepresent extensive experimental results on ZJU-MoCap and PeopleSnapshot toclearly demonstrate the effectiveness of our proposed model. YOTO showsstate-of-the-art performance on all evaluation metrics while showingsignificant benefits in training and inference efficiency as well as renderingquality. The code and model will be made publicly available soon.

You Only Train Once: Multi-Identity Free-Viewpoint Neural Human Rendering from Monocular Videos