Causal Motion Tokenizer for Streaming Motion Generation

Biao Jiang, Xin Chen, Ailing Zeng, Xinru Sun, Fukun Yin, Xianfang Zeng, Chi Zhang, Xuanyang Zhang, Gang Yu, Tao Chen

Keywords: 3d motion, motion generation, human motion synthesis, text-driven, text-to-motion

TL;DR: We proposes a pipeline that continuously generates human motion from text, ensuring smooth transitions and low latency.

Abstract: Recent advancements in human motion generation have leveraged various multimodal inputs, including text, music, and audio. Despite significant progress, the challenge of generating human motion in a streaming context—particularly from text—remains underexplored. Traditional methods often rely on temporal modalities, leaving text-based motion generation with limited capabilities, especially regarding seamless transitions and low latency. In this work, we introduce MotionStream, a pioneering motion-streaming pipeline designed to continuously generate human motion sequences that adhere to the semantic constraints of input text. Our approach utilizes a Causal Motion Tokenizer, built on residual vector quantized variational autoencoder (RVQ-VAE) with causal convolution, to enhance long sequence handling and ensure smooth transitions between motion segments. Furthermore, we employ a Masked Transformer and Residual Transformer to generate motion tokens efficiently. Extensive experiments validate that MotionStream not only achieves state-of-the-art performance in motion composition but also maintains real-time generation capabilities with significantly reduced latency. We highlight the versatility of MotionStream through a story-to-motion application, demonstrating its potential for robotic control, animation, and gaming.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2308