You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 9887 - 9897
• Main Authors: Ng, Evonne, Xiang, Donglai, Joo, Hanbyul, Grauman, Kristen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2020
• Subjects: Cameras; Feature extraction; Pose estimation; Predictive models; Robot vision systems; Three-dimensional displays; Visualization
• ISSN: 1063-6919
• DOI: 10.1109/CVPR42600.2020.00991

The body pose of a person wearing a camera is of great interest for applications in augmented reality, healthcare, and robotics, yet much of the person's body is out of view for a typical wearable camera. We propose a learning-based approach to estimate the camera wearer's 3D body pose from egocentric video sequences. Our key insight is to leverage interactions with another person---whose body pose we can directly observe---as a signal inherently linked to the body pose of the first-person subject. We show that since interactions between individuals often induce a well-ordered series of back-and-forth responses, it is possible to learn a temporal model of the interlinked poses even though one party is largely out of view. We demonstrate our idea on a variety of domains with dyadic interaction and show the substantial impact on egocentric body pose estimation, which improves the state of the art.