GVA：从单目视频重建生动的3D高斯化身
GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos
AI总结：
本文提出GVA方法，通过姿态细化与表面引导重初始化，从单目视频重建高保真3D高斯化身，实现照片级真实感新视角合成及精细姿态控制。
摘要：
在本文中，我们提出了一种新颖的方法，能够从单目视频输入中促进生动的3D高斯化身（GVA）的创建。我们的创新在于解决交付高保真人体重建以及将3D高斯与人体皮肤表面精确对齐的复杂挑战。本文的关键贡献有两方面。首先，我们引入了一种姿态细化技术，通过对齐法线图和轮廓来提高手部和脚部的姿态精度。精确的姿态对于正确的形状和外观重建至关重要。其次，我们解决了先前降低3D高斯化身质量的不平衡聚合和初始化偏差问题，通过一种新颖的表面引导的重新初始化方法，确保3D高斯点与化身表面的精确对齐。实验结果表明，我们提出的方法实现了高保真且生动的3D高斯化身重建。广泛的实验分析在定性和定量上验证了性能，表明其在照片级真实感的新视角合成方面达到了最先进的性能，同时提供了对人体和手部姿态的细粒度控制。项目页面：https://3d-aigc.github.io/GVA/。
英文摘要：
In this paper, we present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA). Our innovation lies in addressing the intricate challenges of delivering high-fidelity human body reconstructions and aligning 3D Gaussians with human skin surfaces accurately. The key contributions of this paper are twofold. Firstly, we introduce a pose refinement technique to improve hand and foot pose accuracy by aligning normal maps and silhouettes. Precise pose is crucial for correct shape and appearance reconstruction. Secondly, we address the problems of unbalanced aggregation and initialization bias that previously diminished the quality of 3D Gaussian avatars, through a novel surface-guided re-initialization method that ensures accurate alignment of 3D Gaussian points with avatar surfaces. Experimental results demonstrate that our proposed method achieves high-fidelity and vivid 3D Gaussian avatar reconstruction. Extensive experimental analyses validate the performance qualitatively and quantitatively, demonstrating that it achieves state-of-the-art performance in photo-realistic novel view synthesis while offering fine-grained control over the human body and hand pose. Project page: https://3d-aigc.github.io/GVA/.
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。
