Dance recalibration for dance coherency with recurrent convolution block

TL;DR

This paper introduces R-Lodge, an improved dance generation model that enhances motion consistency by incorporating recurrent dance recalibration, leading to more coherent dance sequences in AI-generated content.

Contribution

The paper presents R-Lodge, a novel recurrent dance recalibration method that improves coherence in AI-generated dance sequences over prior coarse-to-fine models.

Findings

R-Lodge improves dance motion consistency.

Enhanced coherence in generated dance sequences.

Effective on FineDance dataset.

Abstract

With the recent advancements in generative AI such as GAN, Diffusion, and VAE, the use of generative AI for dance generation has seen significant progress and received considerable interest. In this study, We propose R-Lodge, an enhanced version of Lodge. R-Lodge incorporates Recurrent Sequential Representation Learning named Dance Recalibration to original coarse-to-fine long dance generation model. R-Lodge utilizes Dance Recalibration method using $N$ Dance Recalibration Block to address the lack of consistency in the coarse dance representation of the Lodge model. By utilizing this method, each generated dance motion incorporates a bit of information from the previous dance motions. We evaluate R-Lodge on FineDance dataset and the results show that R-Lodge enhances the consistency of the whole generated dance motions.