UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture. (arXiv:2208.01633v1 [cs.CV])

Web: http://arxiv.org/abs/2208.01633

We present UnrealEgo, i.e., a new large-scale naturalistic dataset for
egocentric 3D human pose estimation. UnrealEgo is based on an advanced concept
of eyeglasses equipped with two fisheye cameras that can be used in
unconstrained environments. We design their virtual prototype and attach them
to 3D human models for stereo view capture. We next generate a large corpus of
human motions. As a consequence, UnrealEgo is the first dataset to provide
in-the-wild stereo images with the largest variety of motions …

3d arxiv cv dataset human motion capture