Aug 2026· SIGGRAPH Asia Conference Papers· 3 citations· 69 references
Computer Science
TL;DR
Inspired by the workflows of expert choreographers, CustomDance introduces a novel paradigm to AI-assisted choreography through three interconnected stages that highlights the significant creative utility and empowering potential of the authors' AI-assisted choreography paradigm, but also outperforms competitive baselines across quantitative and qualitative comparisons.
Abstract
With the rise of AI-generated content (AIGC) and advanced techniques for 3D human representation, the task of generating 3D dance movements has become an exciting area of research. Despite significant advancements, current methods often fail to provide comprehensive and distinct control over various multimodal inputs from users, such as music or specific descriptions of desired movements. As a result, the generated motions may be statistically plausible and technically correct, but they often lack depth, expressiveness, and alignment with the user's creative vision. To address this issue, we present CustomDance, a coarse-to-fine interactive system designed for customized 3D dance generation. Inspired by the workflows of expert choreographers, CustomDance introduces a novel paradigm to AI-assisted choreography through three interconnected stages. First, a multimodal Large Language Model (MLLM) analyzes the music and a high-level text prompt to identify key temporal anchors and creative cues for the piece. Next, for each anchor, a multimodal retriever suggests high-quality motion clips from a dance library based on local music and text, empowering the user with concrete and predictable options. Finally, a custom music-conditioned diffusion in-painter seamlessly connects the selected phrases, allowing for iterative, user-guided refinement of the final composition, supported by visualizations of motion dynamics. Our evaluations demonstrate that CustomDance not only highlights the significant creative utility and empowering potential of our AI-assisted choreography paradigm, but also outperforms competitive baselines across quantitative and qualitative comparisons. Project page: https://github.com/XulongT/CustomDance
Deriving vivid and expressive 3D human dance from music signals has gained tremendous progress in virtual avatar animation. Existing approaches typically overlook the diversity of human body shapes and generate dance motions using standardized body representations, without explicitly modeling the intrinsic relationship...
Mu-Yi Sun, Ze-Zhao Tian, Xing-Qun Qi et al.· International Journal of Com...· 0 citations
Experimental results show that L-DANCE improves instruction alignment and controllability over single-pass and rule-based baselines whilst preserving motion quality and rhythmic consistency, showing the effectiveness of combining LLM-based planning with learned motion-intensity-aware selection for controllable music-dr...
Wonseop Shin, Yonghoon Jung, Mi-Young Lee et al.· The Visual Computer· 0 citations
People often want garments that reflect their aesthetic preferences, fit their bodies, and meet their sizing needs, yet turning these requirements into physical garments remains difficult. Ready-to-wear options provide limited personalization, while custom tailoring is costly and time-consuming. Recent generative artif...
Hong Qu, Zhao-Xiang Xu, Jin-Bo Luo et al.· 0 citations
Paintings encode what cognitive science calls implied motion: the movement that the artist freezes at a chosen instant and that the viewer’s perceptual system completes. This motion also carries expressive and affective qualities, a property we term Implied Expressive Motion (IEM). Generating this motion computationall...
Mohammad S. Mahmoudi, Nicola Corbellini, Cora Gasparotti et al.· Companion Publication of the...· 0 citations
Current music-to-dance generation methods mainly rely on musical features, limiting precise control over generated movements. In particular, most existing methods with control mechanisms do not support example-based control, in which a user provides a reference motion sequence and the generated dances follow its fine-g...
Meng-Qi Liu, Hao Gao, Haolun Li et al.· IEEE Transactions on Visuali...· 0 citations
Bachata, a partner dance built on close coordination and continuous non-verbal exchange, offers a useful model for understanding how two agents can move, adapt, and make decisions together. Inspired by this embodied interaction, this work introduces The Dance of Togetherness, a physical human-robot teaming (HRT) framew...
F. Sanfilippo, M. H. Zafar, Syed Kumayl Raza Moosavi· Coins· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 18, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 12, 2026
MIT scientists developed a training method to generate models that simulate the effects of human activities on climate much more quickly than other approaches.