A multi-view 2D human parsing backprojection pipeline generates pseudo-ground-truth labels for THuman2.1 meshes, and a PointTransformer trained on geometry alone reaches up to 74.4 mIoU when measured against those pseudo-labels.
Towards real-time and lightweight human parsing with fully convolutional networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Part Segmentation of Human Meshes via Multi-View Human Parsing
A multi-view 2D human parsing backprojection pipeline generates pseudo-ground-truth labels for THuman2.1 meshes, and a PointTransformer trained on geometry alone reaches up to 74.4 mIoU when measured against those pseudo-labels.