InterDance:Reactive 3D Dance Generation with Realistic Duet Interactions
This work addresses the problem of realistic duet dance generation for applications in animation and virtual reality, representing an incremental advance in interactive motion synthesis.
The paper tackles the challenge of generating high-quality 3D duet dance motions by addressing dataset limitations and incomplete motion representations, resulting in a new large-scale dataset and a diffusion-based framework that improves interaction realism as validated through experiments.
Humans perform a variety of interactive motions, among which duet dance is one of the most challenging interactions. However, in terms of human motion generative models, existing works are still unable to generate high-quality interactive motions, especially in the field of duet dance. On the one hand, it is due to the lack of large-scale high-quality datasets. On the other hand, it arises from the incomplete representation of interactive motion and the lack of fine-grained optimization of interactions. To address these challenges, we propose, InterDance, a large-scale duet dance dataset that significantly enhances motion quality, data scale, and the variety of dance genres. Built upon this dataset, we propose a new motion representation that can accurately and comprehensively describe interactive motion. We further introduce a diffusion-based framework with an interaction refinement guidance strategy to optimize the realism of interactions progressively. Extensive experiments demonstrate the effectiveness of our dataset and algorithm.