Heuristic Weakly Supervised 3D Human Pose Estimation

TL;DR

This paper introduces HW-HuP, a weakly supervised method for 3D human pose estimation from monocular RGB images that does not require ground truth 3D data, improving practical applicability in challenging scenarios.

Contribution

HW-HuP is a novel approach that learns from partial pose priors and weak supervision without needing 3D ground truth, enabling effective 3D pose estimation in data-scarce environments.

Findings

Outperforms state-of-the-art in bed and infant pose estimation

Retains competitive accuracy on public benchmarks

Operates without 3D ground truth during inference

Abstract

Monocular 3D human pose estimation from RGB images has attracted significant attention in recent years. However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains. 3D pose data is typically collected with motion capture devices, severely limiting their applicability. In this paper, we present a heuristic weakly supervised 3D human pose (HW-HuP) solution to estimate 3D poses in when no ground truth 3D pose data is available. HW-HuP learns partial pose priors from 3D human pose datasets and uses easy-to-access observations from the target domain to estimate 3D human pose and shape in an optimization and regression cycle. We employ depth data for weak supervision during training, but not inference. We show that HW-HuP meaningfully improves upon state-of-the-art models in two practical settings where 3D pose data can hardly be obtained: human poses in bed, and infant poses in the wild. Furthermore, we show that HW-HuP retains comparable performance to cutting-edge models on public benchmarks, even when such models train on 3D pose data.