UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture
This work addresses the need for robust motion capture in unconstrained settings for applications like VR/AR, but it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of egocentric 3D human pose estimation by introducing UnrealEgo, a large-scale dataset with stereo images from eyeglasses in unconstrained environments, and a benchmark method that outperforms previous state-of-the-art methods in experiments.
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 among existing egocentric datasets. Furthermore, we propose a new benchmark method with a simple but effective idea of devising a 2D keypoint estimation module for stereo inputs to improve 3D human pose estimation. The extensive experiments show that our approach outperforms the previous state-of-the-art methods qualitatively and quantitatively. UnrealEgo and our source codes are available on our project web page.