Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Part Segmentation of Human Meshes via Multi-View Human Parsing

cs.CV · 2025-07-22 · conditional · novelty 4.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Part Segmentation of Human Meshes via Multi-View Human Parsing cs.CV · 2025-07-22 · conditional · none · ref 7

    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.