Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning

TL;DR

This paper introduces a meta-learning approach for 3D human pose estimation in videos that adapts to camera distortions without needing calibration, outperforming existing methods.

Contribution

It proposes a novel MAML-based model that quickly adapts to camera distortions using synthetic data and inference optimization, without requiring calibration.

Findings

Successfully adapts to various distortion levels in testing

Outperforms state-of-the-art methods in accuracy

Does not require camera calibration during testing

Abstract

Existing 3D human pose estimation algorithms trained on distortion-free datasets suffer performance drop when applied to new scenarios with a specific camera distortion. In this paper, we propose a simple yet effective model for 3D human pose estimation in video that can quickly adapt to any distortion environment by utilizing MAML, a representative optimization-based meta-learning algorithm. We consider a sequence of 2D keypoints in a particular distortion as a single task of MAML. However, due to the absence of a large-scale dataset in a distorted environment, we propose an efficient method to generate synthetic distorted data from undistorted 2D keypoints. For the evaluation, we assume two practical testing situations depending on whether a motion capture sensor is available or not. In particular, we propose Inference Stage Optimization using bone-length symmetry and consistency. Extensive evaluation shows that our proposed method successfully adapts to various degrees of distortion in the testing phase and outperforms the existing state-of-the-art approaches. The proposed method is useful in practice because it does not require camera calibration and additional computations in a testing set-up.