Camera Motion Agnostic 3D Human Pose Estimation

TL;DR

This paper introduces a novel method for 3D human pose estimation that is invariant to camera motion, enabling accurate pose and motion analysis in videos captured with moving cameras by predicting global motion sequences.

Contribution

The paper proposes a camera motion agnostic approach using a bidirectional GRU network to estimate global motion differences, improving 3D pose estimation in moving-camera scenarios.

Findings

Effective in moving-camera environments

Outperforms existing methods on 3DPW and synthetic datasets

Provides publicly available code and datasets

Abstract

Although the performance of 3D human pose and shape estimation methods has improved significantly in recent years, existing approaches typically generate 3D poses defined in camera or human-centered coordinate system. This makes it difficult to estimate a person's pure pose and motion in world coordinate system for a video captured using a moving camera. To address this issue, this paper presents a camera motion agnostic approach for predicting 3D human pose and mesh defined in the world coordinate system. The core idea of the proposed approach is to estimate the difference between two adjacent global poses (i.e., global motion) that is invariant to selecting the coordinate system, instead of the global pose coupled to the camera motion. To this end, we propose a network based on bidirectional gated recurrent units (GRUs) that predicts the global motion sequence from the local pose sequence consisting of relative rotations of joints called global motion regressor (GMR). We use 3DPW and synthetic datasets, which are constructed in a moving-camera environment, for evaluation. We conduct extensive experiments and prove the effectiveness of the proposed method empirically. Code and datasets are available at https://github.com/seonghyunkim1212/GMR