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 Semantics-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 semantic 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.
@article{arxiv.2312.01964,
title = {Semantics-aware Motion Retargeting with Vision-Language Models},
author = {Haodong Zhang and ZhiKe Chen and Haocheng Xu and Lei Hao and Xiaofei Wu and Songcen Xu and Zhensong Zhang and Yue Wang and Rong Xiong},
journal= {arXiv preprint arXiv:2312.01964},
year = {2024}
}