仅用两张图生成逼真手部虚拟形象，30倍提速实时部署。
PHAF-Personalized Hand Avatars in a Flash
- 用两图对齐语义网格并提取高分辨率纹理，快速生成个性化手像。
- 生成速度比现有方法快30倍，多视角渲染质量接近顶尖水平。
- 适合需要快速手部建模的AR/VR应用，可直接接入标准图形引擎。
我们提出PHAF——一种仅需两张图像（背侧与掌侧视图）即可生成高质量多视角渲染的个性化写实手部虚拟形象。相比传统慢速优化方法，PHAF实现纹理的快速生成，适用于边缘设备实时部署。该方法结合语义引导的网格对齐与密集纹理提取，高效传递高频细节；通过视图感知修复网络优化纹理，确保外观平滑连续。模型具备良好泛化能力，支持新视角生成，并基于参数化手部模型实现精准动作模拟，兼容标准图形引擎。实验表明，其视觉保真度与现有方法相当，但纹理生成时间缩短30倍，显著推动AR/VR中的实用化落地。
原文摘要 · Abstract (English)
We present PHAF-Personalized Hand Avatars in a Flash, a personalized photo-realistic hand avatar which provides high quality multi-view renders from just two images (dorsal and palmar views).Unlike slow optimization-based techniques, PHAF generates fast personalized textures for real-time deployment on edge devices. Our approach combines semantic guided mesh alignment and densified texture extraction to transfer high-frequency details efficiently. A view-based inpainting network refines textures ensuring smooth, continuous appearance. PHAF generalizes to novel viewpoints and leverages a parametric hand model for accurate articulations, making it compatible with standard graphics engines. Experiments show it is comparable to existing methods in visual fidelity while drastically reducing texture generation time by 30 times, enabling practical AR/VR applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。