VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908854551314432 |
|---|---|
| author | Zargarbashi, Fatemeh Agrawal, Dhruv Buhmann, Jakob Guay, Martin Coros, Stelian Sumner, Robert W. |
| author_facet | Zargarbashi, Fatemeh Agrawal, Dhruv Buhmann, Jakob Guay, Martin Coros, Stelian Sumner, Robert W. |
| contents | Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion data to facilitate style transfer. Our approach is guided by the insight that content corresponds to coarse motion attributes while style captures the finer, expressive details. To model this hierarchy, we employ Residual Vector Quantized Variational Autoencoders (RVQ-VAEs) to learn a coarse-to-fine representation of motion. We further enhance the disentanglement by integrating codebook learning with contrastive learning and a novel information leakage loss to organize the content and the style across different codebooks. We harness this disentangled representation using our simple and effective inference-time technique Quantized Code Swapping, which enables motion style transfer without requiring any fine-tuning for unseen styles. Our framework demonstrates strong versatility across multiple inference applications, including style transfer, style removal, and motion blending. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02334 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations Zargarbashi, Fatemeh Agrawal, Dhruv Buhmann, Jakob Guay, Martin Coros, Stelian Sumner, Robert W. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion data to facilitate style transfer. Our approach is guided by the insight that content corresponds to coarse motion attributes while style captures the finer, expressive details. To model this hierarchy, we employ Residual Vector Quantized Variational Autoencoders (RVQ-VAEs) to learn a coarse-to-fine representation of motion. We further enhance the disentanglement by integrating codebook learning with contrastive learning and a novel information leakage loss to organize the content and the style across different codebooks. We harness this disentangled representation using our simple and effective inference-time technique Quantized Code Swapping, which enables motion style transfer without requiring any fine-tuning for unseen styles. Our framework demonstrates strong versatility across multiple inference applications, including style transfer, style removal, and motion blending. |
| title | VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.02334 |