DAMA uses body-anchored Gaussians to reconstruct multi-layered 3D avatars from images, achieving clean garment separation, stacking control, and physical plausibility.
Expressive whole-body 3d gaussian avatar
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
baseline 1polarities
baseline 1representative citing papers
Pretraining on 1M wild videos followed by post-training on curated data yields high-fidelity feedforward 3D avatars that generalize across identities, clothing, and lighting with emergent relightability and loose-garment support.
Pruned local linear blendshapes on Gaussians capture pose-dependent appearance changes to deliver high-quality mobile avatars at 120 FPS from multi-view video without pretrained models.
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.
-
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Pretraining on 1M wild videos followed by post-training on curated data yields high-fidelity feedforward 3D avatars that generalize across identities, clothing, and lighting with emergent relightability and loose-garment support.
-
High-Fidelity Mobile Avatars with Pruned Local Blendshapes
Pruned local linear blendshapes on Gaussians capture pose-dependent appearance changes to deliver high-quality mobile avatars at 120 FPS from multi-view video without pretrained models.