arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11693cs.GRcs.AIcs.CV
收藏

OMEGA-Avatar: 从单张图像进行360°高斯avator的一键建模

OMEGA-Avatar: One-shot Modeling of 360° Gaussian Avatars

Chongqing University(重庆大学);University of Chinese Academy of Sciences(中国科学院大学)

Zehao Xia, Yiqun Wang, Zhengda Lu, Kai Liu, Jun Xiao, Peter Wonka

AI总结:

OMEGA-Avatar通过两个创新模块实现了从单张图像生成360°完整且可动画的3D高斯头,提升了全头avator的建模精度和动画能力。

摘要:

从单张图像创建高保真的、可动画的3D avator仍然是一项严峻的挑战。我们确定了avator生成的三个理想属性:1)方法应为前馈式,2)建模360°完整的全头,3)应为可动画的。然而,当前的工作只同时解决了这三个点中的两个。为了解决这些限制,我们提出了OMEGA-Avatar,这是首个前馈框架,能够从单张图像生成通用的、360°完整的、可动画的3D高斯头。从一个前馈且可动画的框架出发,我们通过两个新颖的组件来解决360°全头avator生成问题。首先,为了克服全头avator生成中的头发建模问题,我们引入了一个语义感知的网格变形模块,该模块整合多视角法线以优化带有头发的FLAME头,同时保持其拓扑结构。其次,为了实现有效的前馈解码,我们提出了一个多视角特征摊铺模块,该模块通过可微的双线性摊铺、分层UV映射和视图感知融合,从多个视角的特征中构建一个共享的通用UV表示。这种方法在所有视角下都保持了全局结构的一致性和局部高频细节,确保了360°的一致性,而无需每个实例的优化。广泛的实验表明,OMEGA-Avatar实现了最先进的性能,在360°全头完整性方面显著优于现有基线,同时在不同视角下稳健地保持了身份。

英文摘要:

Creating high-fidelity, animatable 3D avatars from a single image remains a formidable challenge. We identified three desirable attributes of avatar generation: 1) the method should be feed-forward, 2) model a 360° full-head, and 3) should be animation-ready. However, current work addresses only two of the three points simultaneously. To address these limitations, we propose OMEGA-Avatar, the first feed-forward framework that simultaneously generates a generalizable, 360°-complete, and animatable 3D Gaussian head from a single image. Starting from a feed-forward and animatable framework, we address the 360° full-head avatar generation problem with two novel components. First, to overcome poor hair modeling in full-head avatar generation, we introduce a semantic-aware mesh deformation module that integrates multi-view normals to optimize a FLAME head with hair while preserving its topology structure. Second, to enable effective feed-forward decoding of full-head features, we propose a multi-view feature splatting module that constructs a shared canonical UV representation from features across multiple views through differentiable bilinear splatting, hierarchical UV mapping, and visibility-aware fusion. This approach preserves both global structural coherence and local high-frequency details across all viewpoints, ensuring 360° consistency without per-instance optimization. Extensive experiments demonstrate that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360° full-head completeness while robustly preserving identity across different viewpoints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑