Large motion model for unified multi-modal motion generation

M Zhang, D Jin, C Gu, F Hong, Z Cai, J Huang… - … on Computer Vision, 2025 - 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 …

Crowdmogen: Zero-shot text-driven collective motion generation

X Guo, M Zhang, H Xie, C Gu, Z Liu - arXiv preprint arXiv:2407.06188, 2024 - arxiv.org
Crowd Motion Generation is essential in entertainment industries such as animation and
games as well as in strategic fields like urban simulation and planning. This new task …

HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality

Z Hu, G Zhang, Z Yin, D Haeufle, S Schmitt… - arXiv preprint arXiv …, 2024 - arxiv.org
Human hand and head movements are the most pervasive input modalities in extended
reality (XR) and are significant for a wide range of applications. However, prior works on …

ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos

L Shi, P Bürkner, A Bulling - arXiv preprint arXiv:2403.08591, 2024 - arxiv.org
We present ActionDiffusion--a novel diffusion model for procedure planning in instructional
videos that is the first to take temporal inter-dependencies between actions into account in a …

CFSynthesis: Controllable and Free-view 3D Human Video Synthesis

C Liyuan, X Xiaogang, D Wenqi, Y Zesong… - arXiv preprint arXiv …, 2024 - arxiv.org
Human video synthesis aims to create lifelike characters in various environments, with wide
applications in VR, storytelling, and content creation. While 2D diffusion-based methods …