We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision, easily get trapped in local minima, and therefore struggle with the reconstruction of objects with severe self-occlusion or thin structures. Meanwhile, recent neural methods for novel view synthesis, such as NeRF and its variants, use volume rendering to produce a neural scene representation with robustness of optimization, even for highly complex objects. However, extracting high-quality surfaces from this learned implicit representation is difficult because there are not sufficient surface constraints in the representation. In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation. We observe that the conventional volume rendering method causes inherent geometric errors (i.e. bias) for surface reconstruction, and therefore propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision. Experiments on the DTU dataset and the BlendedMVS dataset show that NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.

翻译：本文提出了一种名为NeuS的新型神经曲面重建方法，用于从二维图像输入中高保真地重建物体和场景。现有神经曲面重建方法（如DVR和IDR）需要前景掩码作为监督，容易陷入局部最小值，因此在处理具有严重自遮挡或薄壁结构的物体时效果不佳。同时，近期用于新视角合成的神经方法（如NeRF及其变体）利用体渲染生成具有优化鲁棒性的神经场景表示，即便面对高度复杂的物体也能有效处理。然而，从这种学习到的隐式表示中提取高质量曲面十分困难，因为该表示缺乏足够的曲面约束。在NeuS中，我们提出将曲面表示为有符号距离函数（SDF）的零水平集，并开发了一种新的体渲染方法来训练神经SDF表示。我们观察到传统体渲染方法会导致曲面重建的固有几何误差（即偏差），因此提出一种新公式，该公式在一阶近似下无偏，从而即使在没有掩码监督的情况下也能实现更精确的曲面重建。在DTU数据集和BlendedMVS数据集上的实验表明，NeuS在高品质曲面重建（尤其是对具有复杂结构和自遮挡的物体与场景）方面优于现有最先进方法。