HyperAIHyperAI

Command Palette

Search for a command to run...

3 months ago

Harmonious Group Choreography with Trajectory-Controllable Diffusion

Yuqin Dai Wanlu Zhu Ronghui Li Zeping Ren Xiangzheng Zhou Jixuan Ying Jun Li Jian Yang

Harmonious Group Choreography with Trajectory-Controllable Diffusion

Abstract

Creating group choreography from music is crucial in cultural entertainment and virtual reality, with a focus on generating harmonious movements. Despite growing interest, recent approaches often struggle with two major challenges: multi-dancer collisions and single-dancer foot sliding. To address these challenges, we propose a Trajectory-Controllable Diffusion (TCDiff) framework, which leverages non-overlapping trajectories to ensure coherent and aesthetically pleasing dance movements. To mitigate collisions, we introduce a Dance-Trajectory Navigator that generates collision-free trajectories for multiple dancers, utilizing a distance-consistency loss to maintain optimal spacing. Furthermore, to reduce foot sliding, we present a footwork adaptor that adjusts trajectory displacement between frames, supported by a relative forward-kinematic loss to further reinforce the correlation between movements and trajectories. Experiments demonstrate our method's superiority.

Benchmarks

BenchmarkMethodologyMetrics
motion-synthesis-on-aioz-gdanceTCDiff
FID: 42.39
GMC: 81.48
GMR: 21.12
GenDiv: 14.37
MMC: 0.25
PFC: 0.54
TIF: 0.15

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp