TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915533320880128 |
|---|---|
| author | Dai, Yuqin Zhu, Wanlu Li, Ronghui Li, Xiu Zhang, Zhenyu Li, Jun Yang, Jian |
| author_facet | Dai, Yuqin Zhu, Wanlu Li, Ronghui Li, Xiu Zhang, Zhenyu Li, Jun Yang, Jian |
| contents | Music-driven dance generation has garnered significant attention due to its wide range of industrial applications, particularly in the creation of group choreography. During the group dance generation process, however, most existing methods still face three primary issues: multi-dancer collisions, single-dancer foot sliding and abrupt swapping in the generation of long group dance. In this paper, we propose TCDiff++, a music-driven end-to-end framework designed to generate harmonious group dance. Specifically, to mitigate multi-dancer collisions, we utilize a dancer positioning embedding to encode temporal and identity information. Additionally, we incorporate a distance-consistency loss to ensure that inter-dancer distances remain within plausible ranges. To address the issue of single-dancer foot sliding, we introduce a swap mode embedding to indicate dancer swapping patterns and design a Footwork Adaptor to refine raw motion, thereby minimizing foot sliding. For long group dance generation, we present a long group diffusion sampling strategy that reduces abrupt position shifts by injecting positional information into the noisy input. Furthermore, we integrate a Sequence Decoder layer to enhance the model's ability to selectively process long sequences. Extensive experiments demonstrate that our TCDiff++ achieves state-of-the-art performance, particularly in long-duration scenarios, ensuring high-quality and coherent group dance generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography Dai, Yuqin Zhu, Wanlu Li, Ronghui Li, Xiu Zhang, Zhenyu Li, Jun Yang, Jian Sound Computer Vision and Pattern Recognition Graphics Audio and Speech Processing Music-driven dance generation has garnered significant attention due to its wide range of industrial applications, particularly in the creation of group choreography. During the group dance generation process, however, most existing methods still face three primary issues: multi-dancer collisions, single-dancer foot sliding and abrupt swapping in the generation of long group dance. In this paper, we propose TCDiff++, a music-driven end-to-end framework designed to generate harmonious group dance. Specifically, to mitigate multi-dancer collisions, we utilize a dancer positioning embedding to encode temporal and identity information. Additionally, we incorporate a distance-consistency loss to ensure that inter-dancer distances remain within plausible ranges. To address the issue of single-dancer foot sliding, we introduce a swap mode embedding to indicate dancer swapping patterns and design a Footwork Adaptor to refine raw motion, thereby minimizing foot sliding. For long group dance generation, we present a long group diffusion sampling strategy that reduces abrupt position shifts by injecting positional information into the noisy input. Furthermore, we integrate a Sequence Decoder layer to enhance the model's ability to selectively process long sequences. Extensive experiments demonstrate that our TCDiff++ achieves state-of-the-art performance, particularly in long-duration scenarios, ensuring high-quality and coherent group dance generation. |
| title | TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography |
| topic | Sound Computer Vision and Pattern Recognition Graphics Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.18671 |