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

Humans constantly interact with daily objects to accomplish tasks. Tounderstand such interactions, computers need to reconstruct these from camerasobserving whole-body interaction with scenes. This is challenging due toocclusion between the body and objects, motion blur, depth/scale ambiguities,and the low image resolution of hands and graspable object parts. To make theproblem tractable, the community focuses either on interacting hands, ignoringthe body, or on interacting bodies, ignoring hands. The GRAB dataset addressesdexterous whole-body interaction but uses marker-based MoCap and lacks images,while BEHAVE captures video of body object interaction but lacks hand detail.We address the limitations of prior work with InterCap, a novel method thatreconstructs interacting whole-bodies and objects from multi-view RGB-D data,using the parametric whole-body model SMPL-X and known object meshes. To tacklethe above challenges, InterCap uses two key observations: (i) Contact betweenthe hand and object can be used to improve the pose estimation of both. (ii)Azure Kinect sensors allow us to set up a simple multi-view RGB-D capturesystem that minimizes the effect of occlusion while providing reasonableinter-camera synchronization. With this method we capture the InterCap dataset,which contains 10 subjects (5 males and 5 females) interacting with 10 objectsof various sizes and affordances, including contact with the hands or feet. Intotal, InterCap has 223 RGB-D videos, resulting in 67,357 multi-view frames,each containing 6 RGB-D images. Our method provides pseudo ground-truth bodymeshes and objects for each video frame. Our InterCap method and dataset fillan important gap in the literature and support many research directions. Ourdata and code are areavailable for research purposes.

InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction