MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Tingwu, Dionne, Olivier, De Ruyter, Michael, Minor, David, Rempe, Davis, Zhao, Kaifeng, Petrovich, Mathis, Yuan, Ye, Li, Chenran, Luo, Zhengyi, Robison, Brian, Blackwell, Xavier, Antoniazzi, Bernardo, Peng, Xue Bin, Zhu, Yuke, Yuen, Simon
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917442257682432
author Wang, Tingwu
Dionne, Olivier
De Ruyter, Michael
Minor, David
Rempe, Davis
Zhao, Kaifeng
Petrovich, Mathis
Yuan, Ye
Li, Chenran
Luo, Zhengyi
Robison, Brian
Blackwell, Xavier
Antoniazzi, Bernardo
Peng, Xue Bin
Zhu, Yuke
Yuen, Simon
author_facet Wang, Tingwu
Dionne, Olivier
De Ruyter, Michael
Minor, David
Rempe, Davis
Zhao, Kaifeng
Petrovich, Mathis
Yuan, Ye
Li, Chenran
Luo, Zhengyi
Robison, Brian
Blackwell, Xavier
Antoniazzi, Bernardo
Peng, Xue Bin
Zhu, Yuke
Yuen, Simon
contents Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridging research and production: 1) Real-time scalability: Industry applications demand real-time generation of a vast repertoire of motion skills, while generative methods exhibit significant degradation in quality and scalability under real-time computation constraints, and 2) Integration: Industry applications demand fine-grained multi-modal control involving velocity commands, style selection, and precise keyframes, a need largely unmet by existing text- or tag-driven models. To overcome these limitations, we introduce MotionBricks: a large-scale, real-time generative framework with a two-fold solution. First, we propose a large-scale modular latent generative backbone tailored for robust real-time motion generation, effectively modeling a dataset of over 350,000 motion clips with a single model. Second, we introduce smart primitives that provide a unified, robust, and intuitive interface for authoring both navigation and object interaction. Applications can be designed in a plug-and-play manner like assembling bricks without expert animation knowledge. Quantitatively, we show that MotionBricks produces state-of-the-art motion quality on open-source and proprietary datasets of various scales, while also achieving a real-time throughput of 15,000 FPS with 2ms latency. We demonstrate the flexibility and robustness of MotionBricks in a complete production-level animation demo, covering navigation and object-scene interaction across various styles with a unified model. To showcase our framework's application beyond animation, we deploy MotionBricks on the Unitree G1 humanoid robot to demonstrate its flexibility and generalization for real-time robotic control.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24833
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
Wang, Tingwu
Dionne, Olivier
De Ruyter, Michael
Minor, David
Rempe, Davis
Zhao, Kaifeng
Petrovich, Mathis
Yuan, Ye
Li, Chenran
Luo, Zhengyi
Robison, Brian
Blackwell, Xavier
Antoniazzi, Bernardo
Peng, Xue Bin
Zhu, Yuke
Yuen, Simon
Robotics
Artificial Intelligence
Graphics
Machine Learning
Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridging research and production: 1) Real-time scalability: Industry applications demand real-time generation of a vast repertoire of motion skills, while generative methods exhibit significant degradation in quality and scalability under real-time computation constraints, and 2) Integration: Industry applications demand fine-grained multi-modal control involving velocity commands, style selection, and precise keyframes, a need largely unmet by existing text- or tag-driven models. To overcome these limitations, we introduce MotionBricks: a large-scale, real-time generative framework with a two-fold solution. First, we propose a large-scale modular latent generative backbone tailored for robust real-time motion generation, effectively modeling a dataset of over 350,000 motion clips with a single model. Second, we introduce smart primitives that provide a unified, robust, and intuitive interface for authoring both navigation and object interaction. Applications can be designed in a plug-and-play manner like assembling bricks without expert animation knowledge. Quantitatively, we show that MotionBricks produces state-of-the-art motion quality on open-source and proprietary datasets of various scales, while also achieving a real-time throughput of 15,000 FPS with 2ms latency. We demonstrate the flexibility and robustness of MotionBricks in a complete production-level animation demo, covering navigation and object-scene interaction across various styles with a unified model. To showcase our framework's application beyond animation, we deploy MotionBricks on the Unitree G1 humanoid robot to demonstrate its flexibility and generalization for real-time robotic control.
title MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
topic Robotics
Artificial Intelligence
Graphics
Machine Learning
url https://arxiv.org/abs/2604.24833