A normalizing flow for monocular 3D human mesh recovery is supervised with samples from 2D pose detector heatmaps via MMD and a person-mask loss, reducing implausible hypotheses for invisible joints and improving benchmark accuracy.
Wirkert, Daniel Rahner, Eric W
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery
A normalizing flow for monocular 3D human mesh recovery is supervised with samples from 2D pose detector heatmaps via MMD and a person-mask loss, reducing implausible hypotheses for invisible joints and improving benchmark accuracy.