Additionally, to learn from 2D poses "in the wild", we train an unsupervised 2D domain adapter network to allow for an expansion of 2D data.
Ranked #19 on 3D Human Pose Estimation on MPI-INF-3DHP
We present a weakly supervised approach to estimate 3D pose points, given only 2D pose landmarks.
With the hierarchical cross feature maps, an HCN can effectively uncover additional semantic features which could not be discovered by a conventional CNN.
While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions.