跳到正文
返回论文列表
cs.GR提交于 已译

OMEGA-Avatar: 单帧建模 360° 高斯头像

OMEGA-Avatar: One-shot Modeling of 360{\deg} Gaussian Avatars

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

中文摘要

从单张图像创建高保真、可动画的 3D 头像极具挑战。现有工作通常仅同时满足前馈(feed-forward)、360° 全头部建模和可动画性这三项属性中的两项。OMEGA-Avatar 是首个前馈框架,能从单图生成通用、360° 完整且可动画的 3D 高斯头部。该框架包含两个新组件:一是语义感知网格变形模块,通过整合多视角法线优化带发型的 FLAME 头部,在保持拓扑结构的同时解决毛发建模问题;二是多视角特征泼溅(splatting)模块,利用可微双线性泼溅、分层 UV 映射和可见性感知融合,从多视角特征构建共享规范 UV 表示。该方法在所有视角下保持全局结构一致性和局部高频细节,无需逐实例优化即可确保 360° 一致性。实验表明,OMEGA-Avatar 在 360° 全头部完整性上显著优于现有基线,并稳健地保持身份一致性。

关键要点

  1. 01现有方法难以同时满足前馈、360° 全头部建模和可动画性三项要求。
  2. 02提出 OMEGA-Avatar,首个能单图生成 360° 完整可动画高斯头像的前馈框架。
  3. 03引入语义感知网格变形模块,优化带发型的 FLAME 头部并保留拓扑结构。
  4. 04设计多视角特征泼溅模块,构建共享规范 UV 表示以保障 360° 一致性。
  5. 05实验显示其在 360° 全头部完整性上达到 SOTA,显著优于现有基线。

解读

尚无解读。

原始英文摘要

arXiv:2602.11693v2 Announce Type: replace-cross Abstract: 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{\deg} 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{\deg}-complete, and animatable 3D Gaussian head from a single image. Starting from a feed-forward and animatable framework, we address the 360{\deg} 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{\deg} consistency without per-instance optimization. Extensive experiments demonstrate that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360{\deg} full-head completeness while robustly preserving identity across different viewpoints.

同方向论文 · cs.GR

查看全部 →