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（ENS），一种高效的三维表面重建方法，能够从多视角图像中学习明确定义的连续曲面。该方法采用一系列神经形变场，将连续输入曲面逐步变换为目标形状。通过将网格作为离散曲面代理进行采样，我们借助高效可微光栅化技术训练形变场，从而获得独立于网格的光滑曲面表征。通过将拉普拉斯-贝尔特拉米特征函数作为本征位置编码，与标准外源傅里叶特征协同使用，本方法可捕捉精细曲面细节。相较隐式表征方法，ENS的训练速度提升1-2个数量级，且能提取更高质量的网格，同时保持竞争力的曲面重建性能与实时处理能力。最后，我们将该方法应用于单模型多物体学习，实现不同形状、曲面细节与纹理间的解耦插值。