2023/11/27 by Jiahui Lei, Yufu Wang, Lei, Jiahui +7 · 30 citations
Computer Science · Engineering · #Human Pose and Action Recognition #Face recognition and analysis #Human Motion and Animation
paper · pdf · doi:10.48550/arxiv.2311.16099
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.