ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

TL;DR

ProxyCap introduces a real-time monocular full-body capture system that leverages human-centric proxy-to-motion learning, enabling accurate and physically plausible world-space motion estimation from monocular videos with moving cameras.

Contribution

It presents a novel human-centric proxy-to-motion learning scheme and a contact-aware neural motion descent module for real-time, accurate world-space full-body capture.

Findings

First real-time monocular full-body capture with foot-ground contact.

Achieves accurate world-space motion estimation from monocular videos.

Demonstrates robustness with hand-held moving cameras.

Abstract

Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However, due to the challenges in data collection and network designs, it remains challenging for existing solutions to achieve real-time full-body capture while being accurate in world space. In this work, we introduce ProxyCap, a human-centric proxy-to-motion learning scheme to learn world-space motions from a proxy dataset of 2D skeleton sequences and 3D rotational motions. Such proxy data enables us to build a learning-based network with accurate world-space supervision while also mitigating the generalization issues. For more accurate and physically plausible predictions in world space, our network is designed to learn human motions from a human-centric perspective, which enables the understanding of the same motion captured with different camera trajectories. Moreover, a contact-aware neural motion descent module is proposed in our network so that it can be aware of foot-ground contact and motion misalignment with the proxy observations. With the proposed learning-based solution, we demonstrate the first real-time monocular full-body capture system with plausible foot-ground contact in world space even using hand-held moving cameras. Our project page is https://zhangyux15.github.io/ProxyCapV2.