# VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations

arXiv: https://arxiv.org/abs/2602.02334 · HTML: https://mlsanity.com/paper/2602.02334/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks](https://mlsanity.com/paper/2305.08842/) (2023)
- [Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases](https://mlsanity.com/paper/2201.04439/) (2022)
- [Motion Puzzle: Arbitrary Motion Style Transfer by Body Part](https://mlsanity.com/paper/2202.05274/) (2022)
- [MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations](https://mlsanity.com/paper/2310.10198/) (2023)
- [Robust Training of Vector Quantized Bottleneck Models](https://mlsanity.com/paper/2005.08520/) (2020)
- [SMooDi: Stylized Motion Diffusion Model](https://mlsanity.com/paper/2407.12783/) (2024)
- [Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer](https://mlsanity.com/paper/2406.06508/) (2024)
- [Generative Human Motion Stylization in Latent Space](https://mlsanity.com/paper/2401.13505/) (2024)
- [RSMT: Real-time Stylized Motion Transition for Characters](https://mlsanity.com/paper/2306.11970/) (2023)
- [Style-ERD: Responsive and Coherent Online Motion Style Transfer](https://mlsanity.com/paper/2203.02574/) (2022)
- [MotionAug: Augmentation with Physical Correction for Human Motion Prediction](https://mlsanity.com/paper/2203.09116/) (2022)
- [Vector Quantized Contrastive Predictive Coding for Template-based Music Generation](https://mlsanity.com/paper/2004.10120/) (2020)
- [MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1902.03938/) (2019)
- [Decoupling Contact for Fine-Grained Motion Style Transfer](https://mlsanity.com/paper/2409.05387/) (2024)
- [Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation](https://mlsanity.com/paper/2503.08180/) (2025)

## Built on by (most cited first, 3 of 3)

- [PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation](https://mlsanity.com/paper/2605.07252/) (2026)
- [Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Execution](https://mlsanity.com/paper/2608.28995/) (2026)
- [MorphoStyle: Motion Style Transfer with Morphology Control](https://mlsanity.com/paper/2609.14189/) (2026)

## Abstract (arXiv)

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.