Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909176053104640 |
|---|---|
| author | Li, Ronghui Zhang, YuXiang Zhang, Yachao Zhang, Hongwen Guo, Jie Zhang, Yan Liu, Yebin Li, Xiu |
| author_facet | Li, Ronghui Zhang, YuXiang Zhang, Yachao Zhang, Hongwen Guo, Jie Zhang, Yan Liu, Yebin Li, Xiu |
| contents | We propose Lodge, a network capable of generating extremely long dance sequences conditioned on given music. We design Lodge as a two-stage coarse to fine diffusion architecture, and propose the characteristic dance primitives that possess significant expressiveness as intermediate representations between two diffusion models. The first stage is global diffusion, which focuses on comprehending the coarse-level music-dance correlation and production characteristic dance primitives. In contrast, the second-stage is the local diffusion, which parallelly generates detailed motion sequences under the guidance of the dance primitives and choreographic rules. In addition, we propose a Foot Refine Block to optimize the contact between the feet and the ground, enhancing the physical realism of the motion. Our approach can parallelly generate dance sequences of extremely long length, striking a balance between global choreographic patterns and local motion quality and expressiveness. Extensive experiments validate the efficacy of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10518 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives Li, Ronghui Zhang, YuXiang Zhang, Yachao Zhang, Hongwen Guo, Jie Zhang, Yan Liu, Yebin Li, Xiu Computer Vision and Pattern Recognition Graphics Sound Audio and Speech Processing We propose Lodge, a network capable of generating extremely long dance sequences conditioned on given music. We design Lodge as a two-stage coarse to fine diffusion architecture, and propose the characteristic dance primitives that possess significant expressiveness as intermediate representations between two diffusion models. The first stage is global diffusion, which focuses on comprehending the coarse-level music-dance correlation and production characteristic dance primitives. In contrast, the second-stage is the local diffusion, which parallelly generates detailed motion sequences under the guidance of the dance primitives and choreographic rules. In addition, we propose a Foot Refine Block to optimize the contact between the feet and the ground, enhancing the physical realism of the motion. Our approach can parallelly generate dance sequences of extremely long length, striking a balance between global choreographic patterns and local motion quality and expressiveness. Extensive experiments validate the efficacy of our method. |
| title | Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives |
| topic | Computer Vision and Pattern Recognition Graphics Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.10518 |