Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision

TL;DR

This paper introduces a new large-scale in-the-wild egocentric dataset and a weakly supervised learning method for 3D human pose estimation from a single fisheye camera, outperforming existing approaches.

Contribution

The paper presents a novel dataset (EgoPW) and a weak supervision training strategy leveraging external-view data for egocentric 3D pose estimation.

Findings

Outperforms state-of-the-art methods quantitatively

Achieves accurate 3D pose predictions in wild scenarios

Effectively utilizes external supervision for training

Abstract

Egocentric 3D human pose estimation with a single fisheye camera has drawn a significant amount of attention recently. However, existing methods struggle with pose estimation from in-the-wild images, because they can only be trained on synthetic data due to the unavailability of large-scale in-the-wild egocentric datasets. Furthermore, these methods easily fail when the body parts are occluded by or interacting with the surrounding scene. To address the shortage of in-the-wild data, we collect a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW). This dataset is captured by a head-mounted fisheye camera and an auxiliary external camera, which provides an additional observation of the human body from a third-person perspective during training. We present a new egocentric pose estimation method, which can be trained on the new dataset with weak external supervision. Specifically, we first generate pseudo labels for the EgoPW dataset with a spatio-temporal optimization method by incorporating the external-view supervision. The pseudo labels are then used to train an egocentric pose estimation network. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. The experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.