Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantic-aware Motion retargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantics embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics.

Framework

New Cases (Updated)

New Ablation Study: SAN+VLM

(Note that SAN neglects the finger movemnts.)

New Ablation Study: Different Numbers of Views

BLIP-2 Responses to Failure Cases of Baseline Methods

Comparison with State of the Arts

Ablation Studies

Video Motion Retargeting

More Cases