A Generalized Two-stage Approach to Motion Style Transfer

Tong Guo, Zhiqian Xia, Feng Yu, Haifeng Xia, Siyu Xia; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 6567-6576

This paper addresses the generalized motion style transfer problem, where the main challenge lies in the inability to apply discrete semantic labels for effective constraints. A cross-dataset style transfer framework is introduced to address key limitations in existing motion synthesis methods. Unlike prior approaches that rely on paired data or discrete semantic labels, our model transfers style through AdaIN-based adaptive instance normalization to encode content motion and style motion separately. A dual-path training strategy that combines style transfer generation and self-reconstruction ensures content preservation. Then, the Dual-Stream Denoising Network (DSDN) integrates LSTM processing for dynamic correction and spatio-temporal autoencoders for static motion refinement, with an Adaptive Gating Fusion Unit (AGFU) that dynamically balances stride amplitude and joint angles. Innovations include cross-dataset transfer without predefined labels, raw-sequence LSTM processing for motion correction, and adaptive fusion architecture outperforming single-method approaches. Validated on the HumanML3D and Mocap datasets, our framework demonstrates significantly enhanced cross-dataset style transfer efficacy.