DAMA uses body-anchored Gaussians to reconstruct multi-layered 3D avatars from images, achieving clean garment separation, stacking control, and physical plausibility.
Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3roles
background 1polarities
background 1representative citing papers
A minimal Gaussian splatting avatar pipeline using the Momentum Human Rig achieves the highest reported PSNR on PeopleSnapshot and ZJU-MoCap without learned deformations.
A Dual-UV mapping combined with factorized synthetic data enables animatable 3D avatar reconstruction from one portrait, achieving strong head and upper-body results when trained only on half-body synthetic data.
citing papers explorer
-
DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars
DAMA uses body-anchored Gaussians to reconstruct multi-layered 3D avatars from images, achieving clean garment separation, stacking control, and physical plausibility.
-
Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars
A minimal Gaussian splatting avatar pipeline using the Momentum Human Rig achieves the highest reported PSNR on PeopleSnapshot and ZJU-MoCap without learned deformations.
-
Bringing Your Portrait to 3D Presence
A Dual-UV mapping combined with factorized synthetic data enables animatable 3D avatar reconstruction from one portrait, achieving strong head and upper-body results when trained only on half-body synthetic data.