Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering. However, existing methods based on signed distance function (SDF) are limited to closed surfaces, failing to reconstruct a wide range of real-world objects that contain open-surface structures. In this work, we introduce a new neural rendering framework, coded NeUDF, that can reconstruct surfaces with arbitrary topologies solely from multi-view supervision. To gain the flexibility of representing arbitrary surfaces, NeUDF leverages the unsigned distance function (UDF) as surface representation. While a naive extension of an SDF-based neural renderer cannot scale to UDF, we propose two new formulations of weight function specially tailored for UDF-based volume rendering. Furthermore, to cope with open surface rendering, where the in/out test is no longer valid, we present a dedicated normal regularization strategy to resolve the surface orientation ambiguity. We extensively evaluate our method over a number of challenging datasets, including DTU}, MGN, and Deep Fashion 3D. Experimental results demonstrate that nEudf can significantly outperform the state-of-the-art method in the task of multi-view surface reconstruction, especially for complex shapes with open boundaries.

翻译：多视图形状重建因神经隐式表面渲染的最新进展而取得了显著进步。然而，现有基于符号距离函数的方法局限于封闭表面，无法重建大量包含开放曲面结构的真实世界物体。本文提出了一种新的神经渲染框架，称为NeUDF，该框架仅需多视图监督即可重建任意拓扑结构的表面。为获得表示任意表面的灵活性，NeUDF采用无符号距离函数作为表面表示。虽然基于SDF的神经渲染器的简单扩展无法适用于UDF，但我们提出了两种专为基于UDF的体绘制量身定制的权重函数新形式。此外，为应对开放曲面渲染中正/反面测试不再有效的问题，我们提出了一种专门的法线正则化策略来解决表面方向歧义性。我们在多个具有挑战性的数据集上（包括DTU、MGN和Deep Fashion 3D）对该方法进行了全面评估。实验结果表明，NeUDF在多视图表面重建任务中显著优于现有最先进方法，尤其对于具有开放边界的复杂形状。