DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars
For researchers in 3D avatar reconstruction, DAMA provides the first Gaussian-based approach that enforces geometric constraints for multi-layered clothing, enabling physically plausible layering and garment reordering.
DAMA introduces a method for reconstructing 3D clothed avatars from multi-view images that achieves physically plausible layering, clean garment separation, and explicit stacking control, outperforming prior work on the 4D-DRESS dataset in geometry reconstruction, garment separation, penetration rate, and penetration depth.
Existing 3D clothed avatar reconstruction methods achieve high visual fidelity but ignore geometric structure and physical plausibility. They either model clothed humans as a single deformable surface or attempt garment disentanglement without enforcing geometric constraints, resulting in ambiguous garment boundaries and no control over stacking or layer ordering. To address these limitations, we introduce DAMA (Disentangled body-Anchored Gaussians for Controllable Multi-layered Avatars), a 3D avatar reconstruction method that produces physically plausible clothed avatars through a dedicated representation and reconstruction method. At the representation level, we bind Gaussians to SMPL-X faces using barycentric in-plane coordinates and a positive normal offset. Based on this parameterization, the reconstruction method lifts 2D segmentations to body-anchored Gaussians, refines layers using topology-guided correction, and jointly optimizes geometry and appearance. DAMA is the first Gaussian avatar reconstruction method from multi-view images to achieve physically plausible layering, clean garment separation, and explicit stacking control. On the full 4D-DRESS dataset (82 scans), it achieves state-of-the-art performance in geometry reconstruction, garment separation, penetration rate, and penetration depth. The representation further supports user-defined garment reordering and fast conversion of body-conforming garments to simulation-ready meshes. Project Page: https://danieleskandar.github.io/dama/