PiG-Avatar decouples Gaussian avatar geometry from body-template surfaces by anchoring Gaussians in a neural-field-governed volumetric canonical space and using barycentric transport for kinematics, yielding SOTA rendering on complex-clothing benchmarks.
ArXivabs/2106.13629(2021) 4
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
HumANDiff improves motion consistency in human video generation by sampling diffusion noise on an articulated human body template and adding joint appearance-motion prediction plus a geometric consistency loss.
A 3D Gaussian Splatting method for human reconstruction that initializes with SMPL-X and adds region-aware density plus multi-scale hash encoding to preserve fine details under motion while keeping real-time speed.
citing papers explorer
-
PiG-Avatar: Hierarchical Neural-Field-Guided Gaussian Avatars
PiG-Avatar decouples Gaussian avatar geometry from body-template surfaces by anchoring Gaussians in a neural-field-governed volumetric canonical space and using barycentric transport for kinematics, yielding SOTA rendering on complex-clothing benchmarks.
-
HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation
HumANDiff improves motion consistency in human video generation by sampling diffusion noise on an articulated human body template and adding joint appearance-motion prediction plus a geometric consistency loss.
-
High-Fidelity 3D Gaussian Human Reconstruction via Region-Aware Initialization and Geometric Priors
A 3D Gaussian Splatting method for human reconstruction that initializes with SMPL-X and adds region-aware density plus multi-scale hash encoding to preserve fine details under motion while keeping real-time speed.