Dynamic Motion Blending for Versatile Motion Editing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915490775957504 |
|---|---|
| author | Jiang, Nan Li, Hongjie Yuan, Ziye He, Zimo Chen, Yixin Liu, Tengyu Zhu, Yixin Huang, Siyuan |
| author_facet | Jiang, Nan Li, Hongjie Yuan, Ziye He, Zimo Chen, Yixin Liu, Tengyu Zhu, Yixin Huang, Siyuan |
| contents | Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets, which severely hinders their versatility in diverse editing scenarios. We introduce MotionCutMix, an online data augmentation technique that dynamically generates training triplets by blending body part motions based on input text. While MotionCutMix effectively expands the training distribution, the compositional nature introduces increased randomness and potential body part incoordination. To model such a rich distribution, we present MotionReFit, an auto-regressive diffusion model with a motion coordinator. The auto-regressive architecture facilitates learning by decomposing long sequences, while the motion coordinator mitigates the artifacts of motion composition. Our method handles both spatial and temporal motion edits directly from high-level human instructions, without relying on additional specifications or Large Language Models. Through extensive experiments, we show that MotionReFit achieves state-of-the-art performance in text-guided motion editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20724 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Motion Blending for Versatile Motion Editing Jiang, Nan Li, Hongjie Yuan, Ziye He, Zimo Chen, Yixin Liu, Tengyu Zhu, Yixin Huang, Siyuan Computer Vision and Pattern Recognition Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets, which severely hinders their versatility in diverse editing scenarios. We introduce MotionCutMix, an online data augmentation technique that dynamically generates training triplets by blending body part motions based on input text. While MotionCutMix effectively expands the training distribution, the compositional nature introduces increased randomness and potential body part incoordination. To model such a rich distribution, we present MotionReFit, an auto-regressive diffusion model with a motion coordinator. The auto-regressive architecture facilitates learning by decomposing long sequences, while the motion coordinator mitigates the artifacts of motion composition. Our method handles both spatial and temporal motion edits directly from high-level human instructions, without relying on additional specifications or Large Language Models. Through extensive experiments, we show that MotionReFit achieves state-of-the-art performance in text-guided motion editing. |
| title | Dynamic Motion Blending for Versatile Motion Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.20724 |