Recent years have witnessed significant progress in the field of neural surface reconstruction. While the extensive focus was put on volumetric and implicit approaches, a number of works have shown that explicit graphics primitives such as point clouds can significantly reduce computational complexity, without sacrificing the reconstructed surface quality. However, less emphasis has been put on modeling dynamic surfaces with point primitives. In this work, we present a dynamic point field model that combines the representational benefits of explicit point-based graphics with implicit deformation networks to allow efficient modeling of non-rigid 3D surfaces. Using explicit surface primitives also allows us to easily incorporate well-established constraints such as-isometric-as-possible regularisation. While learning this deformation model is prone to local optima when trained in a fully unsupervised manner, we propose to additionally leverage semantic information such as keypoint dynamics to guide the deformation learning. We demonstrate our model with an example application of creating an expressive animatable human avatar from a collection of 3D scans. Here, previous methods mostly rely on variants of the linear blend skinning paradigm, which fundamentally limits the expressivity of such models when dealing with complex cloth appearances such as long skirts. We show the advantages of our dynamic point field framework in terms of its representational power, learning efficiency, and robustness to out-of-distribution novel poses.

翻译：近年来，神经表面重建领域取得了显著进展。尽管大量研究集中于体积方法和隐式方法，但诸多工作表明，点云等显式图形基元可在不牺牲重建表面质量的前提下显著降低计算复杂度。然而，利用点基元对动态表面进行建模的研究相对不足。本文提出一种动态点场模型，该模型结合显式点基元图形的表征优势与隐式变形网络，实现对非刚性3D表面的高效建模。通过使用显式表面基元，我们能够便捷地融入诸如"尽可能等距"正则化等成熟约束条件。当以完全无监督方式训练时，该变形模型易陷入局部最优解，为此我们进一步提出利用关键点动力学等语义信息引导变形学习。我们以从3D扫描集合创建可驱动表情动画的人体化身为例展示模型性能。在此类应用中，传统方法多依赖线性蒙皮混合方案的变体，其在处理长裙等复杂服装外观时存在根本性的表达能力局限。实验结果表明，我们的动态点场框架在表征能力、学习效率及对分布外新颖姿态的鲁棒性方面均具有显著优势。