MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913789514874880 |
|---|---|
| author | Wang, Yilin Guo, Chuan Mu, Yuxuan Javed, Muhammad Gohar Zuo, Xinxin Lu, Juwei Jiang, Hai Cheng, Li |
| author_facet | Wang, Yilin Guo, Chuan Mu, Yuxuan Javed, Muhammad Gohar Zuo, Xinxin Lu, Juwei Jiang, Hai Cheng, Li |
| contents | Generative masked transformers have demonstrated remarkable success across various content generation tasks, primarily due to their ability to effectively model large-scale dataset distributions with high consistency. However, in the animation domain, large datasets are not always available. Applying generative masked modeling to generate diverse instances from a single MoCap reference may lead to overfitting, a challenge that remains unexplored. In this work, we present MotionDreamer, a localized masked modeling paradigm designed to learn internal motion patterns from a given motion with arbitrary topology and duration. By embedding the given motion into quantized tokens with a novel distribution regularization method, MotionDreamer constructs a robust and informative codebook for local motion patterns. Moreover, a sliding window local attention is introduced in our masked transformer, enabling the generation of natural yet diverse animations that closely resemble the reference motion patterns. As demonstrated through comprehensive experiments, MotionDreamer outperforms the state-of-the-art methods that are typically GAN or Diffusion-based in both faithfulness and diversity. Thanks to the consistency and robustness of the quantization-based approach, MotionDreamer can also effectively perform downstream tasks such as temporal motion editing, \textcolor{update}{crowd animation}, and beat-aligned dance generation, all using a single reference motion. Visit our project page: https://motiondreamer.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08959 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer Wang, Yilin Guo, Chuan Mu, Yuxuan Javed, Muhammad Gohar Zuo, Xinxin Lu, Juwei Jiang, Hai Cheng, Li Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Generative masked transformers have demonstrated remarkable success across various content generation tasks, primarily due to their ability to effectively model large-scale dataset distributions with high consistency. However, in the animation domain, large datasets are not always available. Applying generative masked modeling to generate diverse instances from a single MoCap reference may lead to overfitting, a challenge that remains unexplored. In this work, we present MotionDreamer, a localized masked modeling paradigm designed to learn internal motion patterns from a given motion with arbitrary topology and duration. By embedding the given motion into quantized tokens with a novel distribution regularization method, MotionDreamer constructs a robust and informative codebook for local motion patterns. Moreover, a sliding window local attention is introduced in our masked transformer, enabling the generation of natural yet diverse animations that closely resemble the reference motion patterns. As demonstrated through comprehensive experiments, MotionDreamer outperforms the state-of-the-art methods that are typically GAN or Diffusion-based in both faithfulness and diversity. Thanks to the consistency and robustness of the quantization-based approach, MotionDreamer can also effectively perform downstream tasks such as temporal motion editing, \textcolor{update}{crowd animation}, and beat-aligned dance generation, all using a single reference motion. Visit our project page: https://motiondreamer.github.io/ |
| title | MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2504.08959 |