Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training
This work addresses the problem of improving pose estimation accuracy and smoothness for applications in 3D fields, representing an incremental advancement over prior methods.
The paper tackled the challenge of incorporating complex human motion priors into video pose estimation by decomposing holistic motion prior into joint motion prior and using adversarial training, resulting in a 9% lower PA-MPJPE and 29% lower acceleration error on the 3DPW dataset.
Estimating human pose from video is a task that receives considerable attention due to its applicability in numerous 3D fields. The complexity of prior knowledge of human body movements poses a challenge to neural network models in the task of regressing keypoints. In this paper, we address this problem by incorporating motion prior in an adversarial way. Different from previous methods, we propose to decompose holistic motion prior to joint motion prior, making it easier for neural networks to learn from prior knowledge thereby boosting the performance on the task. We also utilize a novel regularization loss to balance accuracy and smoothness introduced by motion prior. Our method achieves 9\% lower PA-MPJPE and 29\% lower acceleration error than previous methods tested on 3DPW. The estimator proves its robustness by achieving impressive performance on in-the-wild dataset.