PHD personalizes 3D human pose fitting by calibrating body shape once, then using a shape-conditioned point diffusion prior, PointDiT, to guide optimization, improving absolute and local pose accuracy on EMDB.
Learned vertex descent: A new direction for 3d human model fitting
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
-
PHD: Personalized 3D Human Body Fitting with Point Diffusion
PHD personalizes 3D human pose fitting by calibrating body shape once, then using a shape-conditioned point diffusion prior, PointDiT, to guide optimization, improving absolute and local pose accuracy on EMDB.