Large motion model for unified multi-modal motion generation

M Zhang, D **, C Gu, F Hong, Z Cai, J Huang… - … on Computer Vision, 2024 - Springer
Human motion generation, a cornerstone technique in animation and video production, has
widespread applications in various tasks like text-to-motion and music-to-dance. Previous …

DanceGen: Supporting Choreography Ideation and Prototy** with Generative AI

Y Liu, M Sra - Proceedings of the 2024 ACM Designing Interactive …, 2024 - dl.acm.org
Choreography creation requires high proficiency in artistic and technical skills.
Choreographers typically go through four stages to create a dance piece: preparation …

DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer

Z Ma, X Zhu, G Qi, C Qian, Z Zhang, Z Lei - arxiv preprint arxiv …, 2024 - arxiv.org
Speech-driven 3D facial animation is important for many multimedia applications. Recent
work has shown promise in using either Diffusion models or Transformer architectures for …

Scalable Group Choreography via Variational Phase Manifold Learning

N Le, K Do, X Bui, T Do, E Tjiputra, QD Tran… - … on Computer Vision, 2024 - Springer
Generating group dance motion from the music is a challenging task with several industrial
applications. Although several methods have been proposed to tackle this problem, most of …

Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation

Z Huang, X Xu, C Xu, H Zhang, C Zheng, J Qin… - European Conference on …, 2024 - Springer
Dance, as an art form, fundamentally hinges on the precise synchronization with musical
beats. However, achieving aesthetically pleasing dance sequences from music is …

Music-driven synchronous dance generation considering K-pop musical and choreographical characteristics

S Kim, K Lee - IEEE Access, 2024 - ieeexplore.ieee.org
Generating dance movements from music has been considered a highly challenging task,
as it requires the model to comprehend concepts from two different modalities: audio and …

InterDance: Reactive 3D Dance Generation with Realistic Duet Interactions

R Li, Y Zhang, Y Zhang, Y Zhang, M Su, J Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

Dance Any Beat: Blending Beats with Visuals in Dance Video Generation

X Wang, H Wang, D Liu, W Cai - arxiv preprint arxiv:2405.09266, 2024 - arxiv.org
The task of generating dance from music is crucial, yet current methods, which mainly
produce joint sequences, lead to outputs that lack intuitiveness and complicate data …

CoDancers: Music-Driven Coherent Group Dance Generation with Choreographic Unit

K Yang, X Tang, R Diao, H Liu, J He, Z Fan - Proceedings of the 2024 …, 2024 - dl.acm.org
Dance and music are intimately interconnected, with group dance being a crucial part of
dance artistry. Consequently, Music-Driven Group Dance Generation has been a …

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization

X Tan, H Wang, X Geng, P Zhou - arxiv preprint arxiv:2412.05095, 2024 - arxiv.org
Text-to-motion generation is essential for advancing the creative industry but often presents
challenges in producing consistent, realistic motions. To address this, we focus on fine …