Saved in:
Bibliographic Details
Main Authors: Pan, Dongwei, Guo, Longwei, Guan, Jiazhi, Huang, Luying, Li, Yiding, Liu, Haojie, Feng, Haocheng, He, Wei, Wang, Kaisiyuan, Zhou, Hang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.23132
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917359600533504
author Pan, Dongwei
Guo, Longwei
Guan, Jiazhi
Huang, Luying
Li, Yiding
Liu, Haojie
Feng, Haocheng
He, Wei
Wang, Kaisiyuan
Zhou, Hang
author_facet Pan, Dongwei
Guo, Longwei
Guan, Jiazhi
Huang, Luying
Li, Yiding
Liu, Haojie
Feng, Haocheng
He, Wei
Wang, Kaisiyuan
Zhou, Hang
contents Despite progress in speech-to-video synthesis, existing methods often struggle to capture cross-individual dependencies and provide fine-grained control over reactive behaviors in dyadic settings. To address these challenges, we propose InterDyad, a framework that enables naturalistic interactive dynamics synthesis via querying structural motion guidance. Specifically, we first design an Interactivity Injector that achieves video reenactment based on identity-agnostic motion priors extracted from reference videos. Building upon this, we introduce a MetaQuery-based modality alignment mechanism to bridge the gap between conversational audio and these motion priors. By leveraging a Multimodal Large Language Model (MLLM), our framework is able to distill linguistic intent from audio to dictate the precise timing and appropriateness of reactions. To further improve lip-sync quality under extreme head poses, we propose Role-aware Dyadic Gaussian Guidance (RoDG) for enhanced lip-synchronization and spatial consistency. Finally, we introduce a dedicated evaluation suite with novelly designed metrics to quantify dyadic interaction. Comprehensive experiments demonstrate that InterDyad significantly outperforms state-of-the-art methods in producing natural and contextually grounded two-person interactions. Please refer to our project page for demo videos: https://interdyad.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23132
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance
Pan, Dongwei
Guo, Longwei
Guan, Jiazhi
Huang, Luying
Li, Yiding
Liu, Haojie
Feng, Haocheng
He, Wei
Wang, Kaisiyuan
Zhou, Hang
Computer Vision and Pattern Recognition
Despite progress in speech-to-video synthesis, existing methods often struggle to capture cross-individual dependencies and provide fine-grained control over reactive behaviors in dyadic settings. To address these challenges, we propose InterDyad, a framework that enables naturalistic interactive dynamics synthesis via querying structural motion guidance. Specifically, we first design an Interactivity Injector that achieves video reenactment based on identity-agnostic motion priors extracted from reference videos. Building upon this, we introduce a MetaQuery-based modality alignment mechanism to bridge the gap between conversational audio and these motion priors. By leveraging a Multimodal Large Language Model (MLLM), our framework is able to distill linguistic intent from audio to dictate the precise timing and appropriateness of reactions. To further improve lip-sync quality under extreme head poses, we propose Role-aware Dyadic Gaussian Guidance (RoDG) for enhanced lip-synchronization and spatial consistency. Finally, we introduce a dedicated evaluation suite with novelly designed metrics to quantify dyadic interaction. Comprehensive experiments demonstrate that InterDyad significantly outperforms state-of-the-art methods in producing natural and contextually grounded two-person interactions. Please refer to our project page for demo videos: https://interdyad.github.io/.
title InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.23132