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

Synthesizing 3D human motion plays an important role in many graphicsapplications as well as understanding human activity. While many efforts havebeen made on generating realistic and natural human motion, most approachesneglect the importance of modeling human-scene interactions and affordance. Onthe other hand, affordance reasoning (e.g., standing on the floor or sitting onthe chair) has mainly been studied with static human pose and gestures, and ithas rarely been addressed with human motion. In this paper, we propose tobridge human motion synthesis and scene affordance reasoning. We present ahierarchical generative framework to synthesize long-term 3D human motionconditioning on the 3D scene structure. Building on this framework, we furtherenforce multiple geometry constraints between the human mesh and scene pointclouds via optimization to improve realistic synthesis. Our experiments showsignificant improvements over previous approaches on generating natural andphysically plausible human motion in a scene.

Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes