# Controllable Group Choreography using Contrastive Diffusion Source: [Controllable Group Choreography using Contrastive Diffusion]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:12:36.800Z Authors: Nhat Le, Tuong Do, Khoa Do, Hien Nguyen, Erman Tjiputra, Quang D. Tran, Anh Nguyen Published: 2023-10-29T11:59:12.000Z ## Abstract Music-driven group choreography poses a considerable challenge but holds significant potential for a wide range of industrial applications. The ability to generate synchronized and visually appealing group dance motions that are aligned with music opens up opportunities in many fields such as entertainment, advertising, and virtual performances. However, most of the recent works are not able to generate high-fidelity long-term motions, or fail to enable controllable experience. In this work, we aim to address the demand for high-quality and customizable group dance generation by effectively governing the consistency and diversity of group choreographies. In particular, we utilize a diffusion-based generative approach to enable the synthesis of flexible number of dancers and long-term group dances, while ensuring coherence to the input music. Ultimately, we introduce a Group Contrastive Diffusion (GCD) strategy to enhance the connection between dancers and their group, presenting the ability to control the consistency or diversity level of the synthesized group animation via the classifier-guidance sampling technique. Through intensive experiments and evaluation, we demonstrate the effectiveness of our approach in producing visually captivating and consistent group dance motions. The experimental results show the capability of our method to achieve the desired levels of consistency and diversity, while maintaining the overall quality of the generated group choreography. The source code can be found at https://aioz-ai.github.io/GCD ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Group Dance Generation on AIOZ-GDance long-duration (test)](): Group Dance Generation; AIOZ-GDance long-duration (test); GMR: 40.68. - [Group Dance Generation on AIOZ-GDance short-duration](): Group Dance Generation; AIOZ-GDance short-duration; GMR: 30.22. - [Group Dance Generation on AIST-M 1.0 (test)](): Group Dance Generation; AIST-M 1.0 (test); FID: 35.36. - [Group Dance Generation on AIOZ-GDANCE 1.0 (test)](): Group Dance Generation; AIOZ-GDANCE 1.0 (test); FID: 31.16. - [Multi-dancer movement generation on AIOZ-GDance (test)](): Multi-dancer movement generation; AIOZ-GDance (test); GMR: 38.43. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()