A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights

W Lei, J Wang, F Ma, G Huang, L Liu - arxiv preprint arxiv:2407.08428, 2024 - arxiv.org
Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D
human body video sequences with generative models given control conditions such as text …

X-Dyna: Expressive Dynamic Human Image Animation

D Chang, H Xu, Y **e, Y Gao, Z Kuang, S Cai… - arxiv preprint arxiv …, 2025 - arxiv.org
We introduce X-Dyna, a novel zero-shot, diffusion-based pipeline for animating a single
human image using facial expressions and body movements derived from a driving video …

Human motion video generation: A survey

H Xue, X Luo, Z Hu, X Zhang, X **ang, Y Dai, J Liu… - Authorea …, 2024 - techrxiv.org
Human motion video generation has garnered significant research interest due to its broad
applications, enabling innovations such as photorealistic singing heads or dynamic avatars …

DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses

Y Pang, B Zhu, B Lin, M Zheng, FEH Tay… - arxiv preprint arxiv …, 2024 - arxiv.org
In this work, we present DreamDance, a novel method for animating human images using
only skeleton pose sequences as conditional inputs. Existing approaches struggle with …

MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls

Y Bian, A Zeng, X Ju, X Liu, Z Zhang, W Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Whole-body multimodal motion generation, controlled by text, speech, or music, has
numerous applications including video generation and character animation. However …

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

C Liyuan, X **aogang, 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 …