Skip to yearly menu bar Skip to main content


GART: Gaussian Articulated Template Models

Jiahui Lei · Yufu Wang · Georgios Pavlakos · Lingjie Liu · Kostas Daniilidis

Arch 4A-E Poster #33
award Highlight
[ ]
Fri 21 Jun 10:30 a.m. PDT — noon PDT


We introduce Gaussian Articulated Template Model (GART), an explicit, efficient, and expressive representation for non-rigid articulated subject capturing and rendering from monocular videos. GART utilizes a mixture of moving 3D Gaussians to explicitly approximate a deformable subject’s geometry and appearance. It takes advantage of a categorical template model prior (SMPL, SMAL, etc.) with learnable forward skinning while further generalizing to more complex non-rigid deformations with novel latent bones. GART can be reconstructed via differentiable rendering from monocular videos in seconds or minutes and rendered in novel poses faster than 150fps.

Live content is unavailable. Log in and register to view live content