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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recent progress in 4D implicit representation focuses on globally controllingthe shape and motion with low dimensional latent vectors, which is prone tomissing surface details and accumulating tracking error. While many deep localrepresentations have shown promising results for 3D shape modeling, their 4Dcounterpart does not exist yet. In this paper, we fill this blank by proposinga novel Local 4D implicit Representation for Dynamic clothed human, named LoRD,which has the merits of both 4D human modeling and local representation, andenables high-fidelity reconstruction with detailed surface deformations, suchas clothing wrinkles. Particularly, our key insight is to encourage the networkto learn the latent codes of local part-level representation, capable ofexplaining the local geometry and temporal deformations. To make the inferenceat test-time, we first estimate the inner body skeleton motion to track localparts at each time step, and then optimize the latent codes for each part viaauto-decoding based on different types of observed data. Extensive experimentsdemonstrate that the proposed method has strong capability for representing 4Dhuman, and outperforms state-of-the-art methods on practical applications,including 4D reconstruction from sparse points, non-rigid depth fusion, bothqualitatively and quantitatively.

LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling