InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Yukang, Hong, Yan, Xu, Zunnan, Li, Xindi, Xu, Chao, Song, Chuanbiao, Li, Ronghui, Chen, Haoxing, Lan, Jun, Zhu, Huijia, Wang, Weiqiang, Zhang, Jianfu, Li, Xiu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915448504713216
author Lin, Yukang
Hong, Yan
Xu, Zunnan
Li, Xindi
Xu, Chao
Song, Chuanbiao
Li, Ronghui
Chen, Haoxing
Lan, Jun
Zhu, Huijia
Wang, Weiqiang
Zhang, Jianfu
Li, Xiu
author_facet Lin, Yukang
Hong, Yan
Xu, Zunnan
Li, Xindi
Xu, Chao
Song, Chuanbiao
Li, Ronghui
Chen, Haoxing
Lan, Jun
Zhu, Huijia
Wang, Weiqiang
Zhang, Jianfu
Li, Xiu
contents Recent video generation research has focused heavily on isolated actions, leaving interactive motions-such as hand-face interactions-largely unexamined. These interactions are essential for emerging biometric authentication systems, which rely on interactive motion-based anti-spoofing approaches. From a security perspective, there is a growing need for large-scale, high-quality interactive videos to train and strengthen authentication models. In this work, we introduce a novel paradigm for animating realistic hand-face interactions. Our approach simultaneously learns spatio-temporal contact dynamics and biomechanically plausible deformation effects, enabling natural interactions where hand movements induce anatomically accurate facial deformations while maintaining collision-free contact. To facilitate this research, we present InterHF, a large-scale hand-face interaction dataset featuring 18 interaction patterns and 90,000 annotated videos. Additionally, we propose InterAnimate, a region-aware diffusion model designed specifically for interaction animation. InterAnimate leverages learnable spatial and temporal latents to effectively capture dynamic interaction priors and integrates a region-aware interaction mechanism that injects these priors into the denoising process. To the best of our knowledge, this work represents the first large-scale effort to systematically study human hand-face interactions. Qualitative and quantitative results show InterAnimate produces highly realistic animations, setting a new benchmark. Code and data will be made public to advance research.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation
Lin, Yukang
Hong, Yan
Xu, Zunnan
Li, Xindi
Xu, Chao
Song, Chuanbiao
Li, Ronghui
Chen, Haoxing
Lan, Jun
Zhu, Huijia
Wang, Weiqiang
Zhang, Jianfu
Li, Xiu
Computer Vision and Pattern Recognition
Human-Computer Interaction
Recent video generation research has focused heavily on isolated actions, leaving interactive motions-such as hand-face interactions-largely unexamined. These interactions are essential for emerging biometric authentication systems, which rely on interactive motion-based anti-spoofing approaches. From a security perspective, there is a growing need for large-scale, high-quality interactive videos to train and strengthen authentication models. In this work, we introduce a novel paradigm for animating realistic hand-face interactions. Our approach simultaneously learns spatio-temporal contact dynamics and biomechanically plausible deformation effects, enabling natural interactions where hand movements induce anatomically accurate facial deformations while maintaining collision-free contact. To facilitate this research, we present InterHF, a large-scale hand-face interaction dataset featuring 18 interaction patterns and 90,000 annotated videos. Additionally, we propose InterAnimate, a region-aware diffusion model designed specifically for interaction animation. InterAnimate leverages learnable spatial and temporal latents to effectively capture dynamic interaction priors and integrates a region-aware interaction mechanism that injects these priors into the denoising process. To the best of our knowledge, this work represents the first large-scale effort to systematically study human hand-face interactions. Qualitative and quantitative results show InterAnimate produces highly realistic animations, setting a new benchmark. Code and data will be made public to advance research.
title InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2504.10905