Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Yubo, Wang, Weiqiang, Zhao, Sirui, Xu, Tong, Liu, Lin, Chen, Enhong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909659183448064
author Huang, Yubo
Wang, Weiqiang
Zhao, Sirui
Xu, Tong
Liu, Lin
Chen, Enhong
author_facet Huang, Yubo
Wang, Weiqiang
Zhao, Sirui
Xu, Tong
Liu, Lin
Chen, Enhong
contents Recent years have witnessed remarkable advances in audio-driven talking head generation. However, existing approaches predominantly focus on single-character scenarios. While some methods can create separate conversation videos between two individuals, the critical challenge of generating unified conversation videos with multiple physically co-present characters sharing the same spatial environment remains largely unaddressed. This setting presents two key challenges: audio-to-character correspondence control and the lack of suitable datasets featuring multi-character talking videos within the same scene. To address these challenges, we introduce Bind-Your-Avatar, an MM-DiT-based model specifically designed for multi-talking-character video generation in the same scene. Specifically, we propose (1) A novel framework incorporating a fine-grained Embedding Router that binds `who' and `speak what' together to address the audio-to-character correspondence control. (2) Two methods for implementing a 3D-mask embedding router that enables frame-wise, fine-grained control of individual characters, with distinct loss functions based on observed geometric priors and a mask refinement strategy to enhance the accuracy and temporal smoothness of the predicted masks. (3) The first dataset, to the best of our knowledge, specifically constructed for multi-talking-character video generation, and accompanied by an open-source data processing pipeline, and (4) A benchmark for the dual-talking-characters video generation, with extensive experiments demonstrating superior performance over multiple state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19833
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router
Huang, Yubo
Wang, Weiqiang
Zhao, Sirui
Xu, Tong
Liu, Lin
Chen, Enhong
Computer Vision and Pattern Recognition
Recent years have witnessed remarkable advances in audio-driven talking head generation. However, existing approaches predominantly focus on single-character scenarios. While some methods can create separate conversation videos between two individuals, the critical challenge of generating unified conversation videos with multiple physically co-present characters sharing the same spatial environment remains largely unaddressed. This setting presents two key challenges: audio-to-character correspondence control and the lack of suitable datasets featuring multi-character talking videos within the same scene. To address these challenges, we introduce Bind-Your-Avatar, an MM-DiT-based model specifically designed for multi-talking-character video generation in the same scene. Specifically, we propose (1) A novel framework incorporating a fine-grained Embedding Router that binds `who' and `speak what' together to address the audio-to-character correspondence control. (2) Two methods for implementing a 3D-mask embedding router that enables frame-wise, fine-grained control of individual characters, with distinct loss functions based on observed geometric priors and a mask refinement strategy to enhance the accuracy and temporal smoothness of the predicted masks. (3) The first dataset, to the best of our knowledge, specifically constructed for multi-talking-character video generation, and accompanied by an open-source data processing pipeline, and (4) A benchmark for the dual-talking-characters video generation, with extensive experiments demonstrating superior performance over multiple state-of-the-art methods.
title Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.19833