Large motion model for unified multi-modal motion generation
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 …
widespread applications in various tasks like text-to-motion and music-to-dance. Previous …
Crowdmogen: Zero-shot text-driven collective motion generation
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 …
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
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 …
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
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 …
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 …
applications in VR, storytelling, and content creation. While 2D diffusion-based methods …