linear-blend-skinning-ed59d7c9·1 events·first seen Aliases: Linear Blend Skinning
LUNA is a new neural animation model that bypasses Linear Blend Skinning (LBS) and parametric body models to animate 3D human avatars directly from 2D inputs such as images, keypoints, and sketches. A transformer-based motion regressor disentangles global rigid motion from local non-rigid dynamics, while hybrid supervision enables training on both fitted data and unlabeled in-the-wild video. The model achieves competitive visual fidelity to LBS-based approaches and demonstrates zero-shot cross-identity generalization across diverse driving modalities. The authors claim LUNA is the first end-to-end 3D animatable model supporting implicit 2D driving.