IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Bo, Liu, Tao, Chen, Qi, Chen, Xie, Zheng, Zilong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918219405590528
author Chen, Bo
Liu, Tao
Chen, Qi
Chen, Xie
Zheng, Zilong
author_facet Chen, Bo
Liu, Tao
Chen, Qi
Chen, Xie
Zheng, Zilong
contents Talking face generation aims to synthesize realistic speaking portraits from a single image, yet existing methods often rely on explicit optical flow and local warping, which fail to model complex global motions and cause identity drift. We present IMTalker, a novel framework that achieves efficient and high-fidelity talking face generation through implicit motion transfer. The core idea is to replace traditional flow-based warping with a cross-attention mechanism that implicitly models motion discrepancy and identity alignment within a unified latent space, enabling robust global motion rendering. To further preserve speaker identity during cross-identity reenactment, we introduce an identity-adaptive module that projects motion latents into personalized spaces, ensuring clear disentanglement between motion and identity. In addition, a lightweight flow-matching motion generator produces vivid and controllable implicit motion vectors from audio, pose, and gaze cues. Extensive experiments demonstrate that IMTalker surpasses prior methods in motion accuracy, identity preservation, and audio-lip synchronization, achieving state-of-the-art quality with superior efficiency, operating at 40 FPS for video-driven and 42 FPS for audio-driven generation on an RTX 4090 GPU. We will release our code and pre-trained models to facilitate applications and future research.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer
Chen, Bo
Liu, Tao
Chen, Qi
Chen, Xie
Zheng, Zilong
Computer Vision and Pattern Recognition
Artificial Intelligence
Talking face generation aims to synthesize realistic speaking portraits from a single image, yet existing methods often rely on explicit optical flow and local warping, which fail to model complex global motions and cause identity drift. We present IMTalker, a novel framework that achieves efficient and high-fidelity talking face generation through implicit motion transfer. The core idea is to replace traditional flow-based warping with a cross-attention mechanism that implicitly models motion discrepancy and identity alignment within a unified latent space, enabling robust global motion rendering. To further preserve speaker identity during cross-identity reenactment, we introduce an identity-adaptive module that projects motion latents into personalized spaces, ensuring clear disentanglement between motion and identity. In addition, a lightweight flow-matching motion generator produces vivid and controllable implicit motion vectors from audio, pose, and gaze cues. Extensive experiments demonstrate that IMTalker surpasses prior methods in motion accuracy, identity preservation, and audio-lip synchronization, achieving state-of-the-art quality with superior efficiency, operating at 40 FPS for video-driven and 42 FPS for audio-driven generation on an RTX 4090 GPU. We will release our code and pre-trained models to facilitate applications and future research.
title IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.22167