We propose a physics-based method for synthesizing dexterous hand-object...
We present a method for inferring diverse 3D models of human-object
inte...
We introduce TempCLR, a new time-coherent contrastive learning approach ...
We use our hands to interact with and to manipulate objects. Articulated...
Humans are in constant contact with the world as they move through it an...
We introduce the dynamic grasp synthesis task: given an object with a kn...
Learning to regress 3D human body shape and pose (e.g. SMPL parameters) ...
Due to the lack of camera parameter information for in-the-wild images,
...
In natural conversation and interaction, our hands often overlap or are ...
Despite significant progress, we show that state of the art 3D human pos...
Human motion is fundamental to understanding behavior. Despite progress ...
Training accurate 3D human pose estimators requires large amount of 3D
g...
In this paper, we present MultiPoseNet, a novel bottom-up multi-person p...