arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.14778cs.CVcs.GR
收藏

使用发丝对齐的3D高斯进行人类头发重建

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

ETH Zürich(苏黎世联邦理工学院);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Meta;Technical University of Darmstadt(达姆施塔特工业大学)

Egor Zakharov, Vanessa Sklyarova, Michael Black, Giljoo Nam, Justus Thies, Otmar Hilliges

AI总结:

本文提出一种名为Gaussian Haircut的头发建模方法,结合经典发丝和3D高斯的双重表示,从多视图数据生成可直接用于图形引擎的准确真实发丝重建,在合成与真实场景中达到SOTA性能。

摘要:

我们引入了一种新的头发建模方法,该方法使用经典发丝和3D高斯的双重表示,从多视图数据中生成准确且真实的基于发丝的重建。与利用非结构化高斯来建模人类虚拟化身的近期方法不同,我们的方法使用3D多段线(即发丝)来重建头发。这一根本区别使得生成的发型可以直接在现代计算机图形引擎中用于编辑、渲染和模拟。我们的3D提升方法依赖非结构化高斯来生成多视图真实数据,以监督发丝的拟合。发型本身以所谓的发丝对齐3D高斯的形式表示。这种表示使我们能够将基于发丝的头发先验(这对于发型的内部结构真实建模至关重要)与3D高斯泼溅的可微渲染能力相结合。我们的方法名为Gaussian Haircut,在合成和真实场景上进行了评估,并在基于发丝的头发重建任务中展示了最先进的性能。

英文摘要:

We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recent approaches that leverage unstructured Gaussians to model human avatars, our method reconstructs the hair using 3D polylines, or strands. This fundamental difference allows the use of the resulting hairstyles out-of-the-box in modern computer graphics engines for editing, rendering, and simulation. Our 3D lifting method relies on unstructured Gaussians to generate multi-view ground truth data to supervise the fitting of hair strands. The hairstyle itself is represented in the form of the so-called strand-aligned 3D Gaussians. This representation allows us to combine strand-based hair priors, which are essential for realistic modeling of the inner structure of hairstyles, with the differentiable rendering capabilities of 3D Gaussian Splatting. Our method, named Gaussian Haircut, is evaluated on synthetic and real scenes and demonstrates state-of-the-art performance in the task of strand-based hair reconstruction.

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。

↑