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

Full-body egocentric pose estimation from head and hand poses alone hasbecome an active area of research to power articulate avatar representations onheadset-based platforms. However, existing methods over-rely on the indoormotion-capture spaces in which datasets were recorded, while simultaneouslyassuming continuous joint motion capture and uniform body dimensions. Wepropose EgoPoser to overcome these limitations with four main contributions. 1)EgoPoser robustly models body pose from intermittent hand position andorientation tracking only when inside a headset's field of view. 2) We rethinkinput representations for headset-based ego-pose estimation and introduce anovel global motion decomposition method that predicts full-body poseindependent of global positions. 3) We enhance pose estimation by capturinglonger motion time series through an efficient SlowFast module design thatmaintains computational efficiency. 4) EgoPoser generalizes across various bodyshapes for different users. We experimentally evaluate our method and show thatit outperforms state-of-the-art methods both qualitatively and quantitativelywhile maintaining a high inference speed of over 600fps. EgoPoser establishes arobust baseline for future work where full-body pose estimation no longer needsto rely on outside-in capture and can scale to large-scale and unseenenvironments.

EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere