Salvato in:
Dettagli Bibliografici
Autori principali: Ma, Xingpei, Huang, Shenneng, Cai, Jiaran, Guan, Yuansheng, Zheng, Shen, Zhao, Hanfeng, Zhang, Qiang, Zhang, Shunsi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.12089
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908661420392448
author Ma, Xingpei
Huang, Shenneng
Cai, Jiaran
Guan, Yuansheng
Zheng, Shen
Zhao, Hanfeng
Zhang, Qiang
Zhang, Shunsi
author_facet Ma, Xingpei
Huang, Shenneng
Cai, Jiaran
Guan, Yuansheng
Zheng, Shen
Zhao, Hanfeng
Zhang, Qiang
Zhang, Shunsi
contents Recent advances in diffusion models have significantly improved audio-driven human video generation, surpassing traditional methods in both quality and controllability. However, existing approaches still face challenges in lip-sync accuracy, temporal coherence for long video generation, and multi-character animation. In this work, we propose a diffusion transformer (DiT)-based framework for generating lifelike talking videos of arbitrary length, and introduce a training-free method for multi-character audio-driven animation. First, we employ a LoRA-based training strategy combined with a position shift inference approach, which enables efficient long video generation while preserving the capabilities of the foundation model. Moreover, we combine partial parameter updates with reward feedback to enhance both lip synchronization and natural body motion. Finally, we propose a training-free approach, Mask Classifier-Free Guidance (Mask-CFG), for multi-character animation, which requires no specialized datasets or model modifications and supports audio-driven animation for three or more characters. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving high-quality, temporally coherent, and multi-character audio-driven video generation in a simple, efficient, and cost-effective manner.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12089
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback
Ma, Xingpei
Huang, Shenneng
Cai, Jiaran
Guan, Yuansheng
Zheng, Shen
Zhao, Hanfeng
Zhang, Qiang
Zhang, Shunsi
Computer Vision and Pattern Recognition
Recent advances in diffusion models have significantly improved audio-driven human video generation, surpassing traditional methods in both quality and controllability. However, existing approaches still face challenges in lip-sync accuracy, temporal coherence for long video generation, and multi-character animation. In this work, we propose a diffusion transformer (DiT)-based framework for generating lifelike talking videos of arbitrary length, and introduce a training-free method for multi-character audio-driven animation. First, we employ a LoRA-based training strategy combined with a position shift inference approach, which enables efficient long video generation while preserving the capabilities of the foundation model. Moreover, we combine partial parameter updates with reward feedback to enhance both lip synchronization and natural body motion. Finally, we propose a training-free approach, Mask Classifier-Free Guidance (Mask-CFG), for multi-character animation, which requires no specialized datasets or model modifications and supports audio-driven animation for three or more characters. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving high-quality, temporally coherent, and multi-character audio-driven video generation in a simple, efficient, and cost-effective manner.
title Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12089