AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos

TL;DR

AvatarPose introduces a novel approach using personalized neural avatars as priors to accurately estimate 3D poses of closely interacting humans from sparse multi-view videos, overcoming occlusion and contact challenges.

Contribution

The paper presents a new avatar-guided method that reconstructs personalized neural avatars and directly optimizes 3D poses, improving robustness in multi-person close interactions.

Findings

Achieves state-of-the-art results on public datasets.

Effectively handles occlusions and body contact.

Improves pose estimation accuracy in challenging scenarios.

Abstract

Despite progress in human motion capture, existing multi-view methods often face challenges in estimating the 3D pose and shape of multiple closely interacting people. This difficulty arises from reliance on accurate 2D joint estimations, which are hard to obtain due to occlusions and body contact when people are in close interaction. To address this, we propose a novel method leveraging the personalized implicit neural avatar of each individual as a prior, which significantly improves the robustness and precision of this challenging pose estimation task. Concretely, the avatars are efficiently reconstructed via layered volume rendering from sparse multi-view videos. The reconstructed avatar prior allows for the direct optimization of 3D poses based on color and silhouette rendering loss, bypassing the issues associated with noisy 2D detections. To handle interpenetration, we propose a collision loss on the overlapping shape regions of avatars to add penetration constraints. Moreover, both 3D poses and avatars are optimized in an alternating manner. Our experimental results demonstrate state-of-the-art performance on several public datasets.