DAMA uses body-anchored Gaussians to reconstruct multi-layered 3D avatars from images, achieving clean garment separation, stacking control, and physical plausibility.
Learning disentangled avatars with hybrid 3d representations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
AvatarMix introduces direct Gaussian avatar composition with SeamFix and FullbodyFix refinement modules plus mesh retargeting to achieve identity-preserving 3D outfit transfer.
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.
-
AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization
AvatarMix introduces direct Gaussian avatar composition with SeamFix and FullbodyFix refinement modules plus mesh retargeting to achieve identity-preserving 3D outfit transfer.