Choreographers face increasing pressure to create content rapidly, driven by growing demand in social media, entertainment, and commercial sectors, often compromising creativity. This study introduces ChoreoCraft, a novel in-situ virtual reality (VR) choreographic system designed to enhance the creation process of choreography. Through contextual inquiries with professional choreographers, we identified key challenges such as memory dependency, creative plateaus, and abstract feedback to formulate design implications. Then, we propose a VR choreography creation system embedded with a context-aware choreography suggestion system and a choreography analysis system, all grounded in choreographers' creative processes and mental models. Our study results demonstrated that ChoreoCraft fosters creativity, reduces memory dependency, and improves efficiency in choreography creation. Participants reported high satisfaction with the system's ability to overcome creative plateaus and provide objective feedback. Our work advances creativity support tools by providing digital assistance in dance composition that values artistic autonomy while fostering innovation and efficiency.
ChoreoCraft System Overview. Upon entering the VR interface, choreographers listen to the full audio and navigate through segmented counts to begin recording motions. (2-a) The system displays an identical avatar of the choreographer, and (2-b) a snapshot function allows instant playback of recorded motions. When the suggestion function is activated (3), three different suggested motions are visualized using avatars. Choreographers can select an 8-count recorded motion chunk for review (4). The system then provides motion analysis values with corresponding visualizations on the avatar (5-a), allowing choreographers to interpret the analysis (5-b). After reviewing and making modifications, they record a revised motion (6-a). In this example, the motion analysis identified a high dependency on the left wrist (6-b), prompting the choreographer to focus on balancing movement on the right side.
Choreography Suggestion System. We suggest choreographies based on the user’s input music and motion sequence. We extract similar songs and retrieve choreography videos associated with these songs from online sources. Subsequently, we apply 3D pose estimation to convert the videos into 3D motion sequences and utilize DanceDTW to compare the similarity between these sequences and the user’s input motion sequence. Through these processes, we ultimately suggest choreographies that maintain both musical harmony and continuity with previous motions.
The structure of DanceDTW. Input motion (X) and reference motion (Y) undergo offset adjustment (f) and min-max normalization (g), respectively. Positional costs are normalized using function h and summed to obtain the total positional cost (Cp). Rotational costs are directly summed to obtain the total rotational cost (Cr). The final cost (Ctotal) represents the overall similarity between the motions.
Kinematic Factors for Choreography Analysis. The kinematic factors used for choreography analysis were derived from our exploratory study. We considered these factors to encompass Motion Equability, Motion Stability, and Motion Engagement in our analysis.
@inproceedings{han2025choreocraft,
author = {Hyunyoung Han and Kyungeun Jung and Sang Ho Yoon},
title = {ChoreoCraft: Insitu Crafting of Choreography in Virtual Reality through Creativity Support Tool},
booktitle = {CHI Conference on Human Factors in Computing Systems (CHI '25)},
year = {2025},
month = {April},
location = {Yokohama, Japan},
publisher = {ACM},
address = {New York, NY, USA},
pages = {22},
doi = {10.1145/3706598.3714220}
}