FLEX: Full-Body Grasping Without Full-Body Grasps. (arXiv:2211.11903v1 [cs.RO])

Synthesizing 3D human avatars interacting realistically with a scene is an
important problem with applications in AR/VR, video games and robotics. Towards
this goal, we address the task of generating a virtual human -- hands and full
body -- grasping everyday objects. Existing methods approach this problem by
collecting a 3D dataset of humans interacting with objects and training on this
data. However, 1) these methods do not generalize to different object positions
and orientations, or to the presence of …

arxiv flex