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

Recovering high-quality 3D human motion in complex scenes from monocularvideos is important for many applications, ranging from AR/VR to robotics.However, capturing realistic human-scene interactions, while dealing withocclusions and partial views, is challenging; current approaches are still farfrom achieving compelling results. We address this problem by proposing LEMO:LEarning human MOtion priors for 4D human body capture. By leveraging thelarge-scale motion capture dataset AMASS, we introduce a novel motionsmoothness prior, which strongly reduces the jitters exhibited by posesrecovered over a sequence. Furthermore, to handle contacts and occlusionsoccurring frequently in body-scene interactions, we design a contact frictionterm and a contact-aware motion infiller obtained via per-instanceself-supervised training. To prove the effectiveness of the proposed motionpriors, we combine them into a novel pipeline for 4D human body capture in 3Dscenes. With our pipeline, we demonstrate high-quality 4D human body capture,reconstructing smooth motions and physically plausible body-scene interactions.The code and data are available at https://sanweiliti.github.io/LEMO/LEMO.html.

Learning Motion Priors for 4D Human Body Capture in 3D Scenes