Multi-identity Human Image Animation with Structural Video Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zhenzhi, Li, Yixuan, Zeng, Yanhong, Guo, Yuwei, Lin, Dahua, Xue, Tianfan, Dai, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915559019380736
author Wang, Zhenzhi
Li, Yixuan
Zeng, Yanhong
Guo, Yuwei
Lin, Dahua
Xue, Tianfan
Dai, Bo
author_facet Wang, Zhenzhi
Li, Yixuan
Zeng, Yanhong
Guo, Yuwei
Lin, Dahua
Xue, Tianfan
Dai, Bo
contents Generating human videos from a single image while ensuring high visual quality and precise control is a challenging task, especially in complex scenarios involving multiple individuals and interactions with objects. Existing methods, while effective for single-human cases, often fail to handle the intricacies of multi-identity interactions because they struggle to associate the correct pairs of human appearance and pose condition and model the distribution of 3D-aware dynamics. To address these limitations, we present \emph{Structural Video Diffusion}, a novel framework designed for generating realistic multi-human videos. Our approach introduces two core innovations: identity-specific embeddings to maintain consistent appearances across individuals and a structural learning mechanism that incorporates depth and surface-normal cues to model human-object interactions. Additionally, we expand existing human video dataset with 25K new videos featuring diverse multi-human and object interaction scenarios, providing a robust foundation for training. Experimental results demonstrate that Structural Video Diffusion achieves superior performance in generating lifelike, coherent videos for multiple subjects with dynamic and rich interactions, advancing the state of human-centric video generation. Code is available at https://github.com/zhenzhiwang/Multi-HumanVid
format Preprint
id arxiv_https___arxiv_org_abs_2504_04126
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-identity Human Image Animation with Structural Video Diffusion
Wang, Zhenzhi
Li, Yixuan
Zeng, Yanhong
Guo, Yuwei
Lin, Dahua
Xue, Tianfan
Dai, Bo
Computer Vision and Pattern Recognition
Artificial Intelligence
Generating human videos from a single image while ensuring high visual quality and precise control is a challenging task, especially in complex scenarios involving multiple individuals and interactions with objects. Existing methods, while effective for single-human cases, often fail to handle the intricacies of multi-identity interactions because they struggle to associate the correct pairs of human appearance and pose condition and model the distribution of 3D-aware dynamics. To address these limitations, we present \emph{Structural Video Diffusion}, a novel framework designed for generating realistic multi-human videos. Our approach introduces two core innovations: identity-specific embeddings to maintain consistent appearances across individuals and a structural learning mechanism that incorporates depth and surface-normal cues to model human-object interactions. Additionally, we expand existing human video dataset with 25K new videos featuring diverse multi-human and object interaction scenarios, providing a robust foundation for training. Experimental results demonstrate that Structural Video Diffusion achieves superior performance in generating lifelike, coherent videos for multiple subjects with dynamic and rich interactions, advancing the state of human-centric video generation. Code is available at https://github.com/zhenzhiwang/Multi-HumanVid
title Multi-identity Human Image Animation with Structural Video Diffusion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.04126