We introduce Explicit Neural Surfaces (ENS), an efficient surface reconstruction method that learns an explicitly defined continuous surface from multiple views. We use a series of neural deformation fields to progressively transform a continuous input surface to a target shape. By sampling meshes as discrete surface proxies, we train the deformation fields through efficient differentiable rasterization, and attain a mesh-independent and smooth surface representation. By using Laplace-Beltrami eigenfunctions as an intrinsic positional encoding alongside standard extrinsic Fourier features, our approach can capture fine surface details. ENS trains 1 to 2 orders of magnitude faster and can extract meshes of higher quality compared to implicit representations, whilst maintaining competitive surface reconstruction performance and real-time capabilities. Finally, we apply our approach to learn a collection of objects in a single model, and achieve disentangled interpolations between different shapes, their surface details, and textures.

翻译：我们提出显式神经曲面（Explicit Neural Surfaces, ENS），一种高效表面重建方法，可从多视角学习显式定义的连续曲面。通过一系列神经变形场，我们将连续输入曲面逐步变换至目标形状。以离散曲面代理的网格采样为基础，借助高效的微分光栅化训练变形场，从而获得独立于网格的平滑表面表示。该方法采用拉普拉斯-贝尔特拉米本征函数作为内在位置编码，并与标准外蕴傅里叶特征结合，能够捕捉精细表面细节。相较于隐式表示，ENS的训练速度提升1-2个数量级，可提取更高质量的网格，同时保持竞争力的表面重建性能与实时能力。最后，我们将该方法应用于单模型多物体学习，实现了不同形状、表面细节与纹理间的解耦插值。