Hoang-Son Vo-Thanh, Quang-Vinh Nguyen, Soo-Hyung Kim
{"title":"基于 KAN 的双域融合技术,用于音频驱动的面部地标生成","authors":"Hoang-Son Vo-Thanh, Quang-Vinh Nguyen, Soo-Hyung Kim","doi":"arxiv-2409.05330","DOIUrl":null,"url":null,"abstract":"Audio-driven talking face generation is a widely researched topic due to its\nhigh applicability. Reconstructing a talking face using audio significantly\ncontributes to fields such as education, healthcare, online conversations,\nvirtual assistants, and virtual reality. Early studies often focused solely on\nchanging the mouth movements, which resulted in outcomes with limited practical\napplications. Recently, researchers have proposed a new approach of\nconstructing the entire face, including face pose, neck, and shoulders. To\nachieve this, they need to generate through landmarks. However, creating stable\nlandmarks that align well with the audio is a challenge. In this paper, we\npropose the KFusion of Dual-Domain model, a robust model that generates\nlandmarks from audio. We separate the audio into two distinct domains to learn\nemotional information and facial context, then use a fusion mechanism based on\nthe KAN model. Our model demonstrates high efficiency compared to recent\nmodels. This will lay the groundwork for the development of the audio-driven\ntalking face generation problem in the future.","PeriodicalId":501480,"journal":{"name":"arXiv - CS - Multimedia","volume":"33 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation\",\"authors\":\"Hoang-Son Vo-Thanh, Quang-Vinh Nguyen, Soo-Hyung Kim\",\"doi\":\"arxiv-2409.05330\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Audio-driven talking face generation is a widely researched topic due to its\\nhigh applicability. Reconstructing a talking face using audio significantly\\ncontributes to fields such as education, healthcare, online conversations,\\nvirtual assistants, and virtual reality. Early studies often focused solely on\\nchanging the mouth movements, which resulted in outcomes with limited practical\\napplications. Recently, researchers have proposed a new approach of\\nconstructing the entire face, including face pose, neck, and shoulders. To\\nachieve this, they need to generate through landmarks. However, creating stable\\nlandmarks that align well with the audio is a challenge. In this paper, we\\npropose the KFusion of Dual-Domain model, a robust model that generates\\nlandmarks from audio. We separate the audio into two distinct domains to learn\\nemotional information and facial context, then use a fusion mechanism based on\\nthe KAN model. Our model demonstrates high efficiency compared to recent\\nmodels. This will lay the groundwork for the development of the audio-driven\\ntalking face generation problem in the future.\",\"PeriodicalId\":501480,\"journal\":{\"name\":\"arXiv - CS - Multimedia\",\"volume\":\"33 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.05330\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.05330","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
音频驱动的人脸识别技术具有很强的适用性,因此是一个被广泛研究的课题。利用音频重建会说话的人脸对教育、医疗保健、在线对话、虚拟助手和虚拟现实等领域大有裨益。早期的研究通常只关注嘴部动作的变化,结果实际应用有限。最近,研究人员提出了一种新方法,即构建整个面部,包括面部姿势、颈部和肩部。为了实现这一目标,他们需要通过地标来生成。然而,创建与音频完全一致的稳定地标是一项挑战。在本文中,我们提出了 KFusion 双域模型,这是一种从音频生成地标的稳健模型。我们将音频分为两个不同的域来学习情感信息和面部上下文,然后使用基于 KAN 模型的融合机制。与最近的模型相比,我们的模型具有很高的效率。这将为未来开发音频驱动的人脸生成问题奠定基础。
KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation
Audio-driven talking face generation is a widely researched topic due to its
high applicability. Reconstructing a talking face using audio significantly
contributes to fields such as education, healthcare, online conversations,
virtual assistants, and virtual reality. Early studies often focused solely on
changing the mouth movements, which resulted in outcomes with limited practical
applications. Recently, researchers have proposed a new approach of
constructing the entire face, including face pose, neck, and shoulders. To
achieve this, they need to generate through landmarks. However, creating stable
landmarks that align well with the audio is a challenge. In this paper, we
propose the KFusion of Dual-Domain model, a robust model that generates
landmarks from audio. We separate the audio into two distinct domains to learn
emotional information and facial context, then use a fusion mechanism based on
the KAN model. Our model demonstrates high efficiency compared to recent
models. This will lay the groundwork for the development of the audio-driven
talking face generation problem in the future.