Jie Wang;Jiu-Cheng Xie;Xianyan Li;Feng Xu;Chi-Man Pun;Hao Gao
{"title":"高斯头像:高保真头像与可学习的高斯推导。","authors":"Jie Wang;Jiu-Cheng Xie;Xianyan Li;Feng Xu;Chi-Man Pun;Hao Gao","doi":"10.1109/TVCG.2025.3561794","DOIUrl":null,"url":null,"abstract":"Creating lifelike 3D head avatars and generating compelling animations for diverse subjects remain challenging in computer vision. This paper presents GaussianHead, which models the active head based on anisotropic 3D Gaussians. Our method integrates a motion deformation field and a single-resolution tri-plane to capture the head's intricate dynamics and detailed texture. Notably, we introduce a customized derivation scheme for each 3D Gaussian, facilitating the generation of multiple “doppelgangers” through learnable parameters for precise position transformation. This approach enables efficient representation of diverse Gaussian attributes and ensures their precision. Additionally, we propose an inherited derivation strategy for newly added Gaussians to expedite training. Extensive experiments demonstrate GaussianHead's efficacy, achieving high-fidelity visual results with a remarkably compact model size (<inline-formula><tex-math>$\\approx 12$</tex-math></inline-formula> MB). Our method outperforms state-of-the-art alternatives in tasks such as reconstruction, cross-identity reenactment, and novel view synthesis.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"31 7","pages":"4141-4154"},"PeriodicalIF":0.0000,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"GaussianHead: High-Fidelity Head Avatars With Learnable Gaussian Derivation\",\"authors\":\"Jie Wang;Jiu-Cheng Xie;Xianyan Li;Feng Xu;Chi-Man Pun;Hao Gao\",\"doi\":\"10.1109/TVCG.2025.3561794\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Creating lifelike 3D head avatars and generating compelling animations for diverse subjects remain challenging in computer vision. This paper presents GaussianHead, which models the active head based on anisotropic 3D Gaussians. Our method integrates a motion deformation field and a single-resolution tri-plane to capture the head's intricate dynamics and detailed texture. Notably, we introduce a customized derivation scheme for each 3D Gaussian, facilitating the generation of multiple “doppelgangers” through learnable parameters for precise position transformation. This approach enables efficient representation of diverse Gaussian attributes and ensures their precision. Additionally, we propose an inherited derivation strategy for newly added Gaussians to expedite training. Extensive experiments demonstrate GaussianHead's efficacy, achieving high-fidelity visual results with a remarkably compact model size (<inline-formula><tex-math>$\\\\approx 12$</tex-math></inline-formula> MB). Our method outperforms state-of-the-art alternatives in tasks such as reconstruction, cross-identity reenactment, and novel view synthesis.\",\"PeriodicalId\":94035,\"journal\":{\"name\":\"IEEE transactions on visualization and computer graphics\",\"volume\":\"31 7\",\"pages\":\"4141-4154\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-04-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on visualization and computer graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10969103/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on visualization and computer graphics","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10969103/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
GaussianHead: High-Fidelity Head Avatars With Learnable Gaussian Derivation
Creating lifelike 3D head avatars and generating compelling animations for diverse subjects remain challenging in computer vision. This paper presents GaussianHead, which models the active head based on anisotropic 3D Gaussians. Our method integrates a motion deformation field and a single-resolution tri-plane to capture the head's intricate dynamics and detailed texture. Notably, we introduce a customized derivation scheme for each 3D Gaussian, facilitating the generation of multiple “doppelgangers” through learnable parameters for precise position transformation. This approach enables efficient representation of diverse Gaussian attributes and ensures their precision. Additionally, we propose an inherited derivation strategy for newly added Gaussians to expedite training. Extensive experiments demonstrate GaussianHead's efficacy, achieving high-fidelity visual results with a remarkably compact model size ($\approx 12$ MB). Our method outperforms state-of-the-art alternatives in tasks such as reconstruction, cross-identity reenactment, and novel view synthesis.