Unsupervised 3D Human Pose Estimation
5 papers with code • 2 benchmarks • 2 datasets
Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem.
Our approach not only generalizes to in-the-wild images, but also yields a superior trade-off between speed and performance, compared to prior top-down approaches.
To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network.
Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre).
To address the obstacles, our key-idea is to employ non-occluded human data to learn a joint-level spatial-temporal motion prior for occluded human with a self-supervised strategy.