The paper proves exact 3D human motion recovery from 2D landmarks via l1 minimization holds if and only if the newly defined Projective Kinematic Space Property is satisfied.
Learning Latent Representa- tions of 3d Human Pose with Deep Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Exact Recovery Conditions of 3D Human Motion from 2D Landmark Motion with Sparse Articulated Motion
The paper proves exact 3D human motion recovery from 2D landmarks via l1 minimization holds if and only if the newly defined Projective Kinematic Space Property is satisfied.