EventHPE: Event-based 3D Human Pose and Shape Estimation

TL;DR

This paper introduces EventHPE, a two-stage deep learning method for estimating 3D human pose and shape from event camera signals, leveraging unsupervised optical flow inference and a novel flow coherence loss.

Contribution

The paper presents a novel two-stage approach using event data for 3D human pose and shape estimation, including a new dataset with annotations.

Findings

Effective 3D human shape estimation from event data

Unsupervised optical flow improves shape prediction

New dataset with 3D annotations enhances evaluation

Abstract

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: rather than capturing static body postures, the event signals are best at capturing local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, is trained by unsupervised learning to infer optical flow from events. Both events and optical flow are closely related to human body dynamics, which are fed as input to the ShapeNet in the second stage, to estimate 3D human shapes. To mitigate the discrepancy between image-based flow (optical flow) and shape-based flow (vertices movement of human body shape), a novel flow coherence loss is introduced by exploiting the fact that both flows are originated from the identical human motion. An in-house event-based 3D human dataset is curated that comes with 3D pose and shape annotations, which is by far the largest one to our knowledge. Empirical evaluations on DHP19 dataset and our in-house dataset demonstrate the effectiveness of our approach.