Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF learning which exploits a learned geometry prior for efficient training and a novel regularization for robustness to sparse sampling. The core idea of SuperUDF draws inspiration from the classical surface approximation operator of locally optimal projection (LOP). The key insight is that if the UDF is estimated correctly, the 3D points should be locally projected onto the underlying surface following the gradient of the UDF. Based on that, a number of inductive biases on UDF geometry and a pre-learned geometry prior are devised to learn UDF estimation efficiently. A novel regularization loss is proposed to make SuperUDF robust to sparse sampling. Furthermore, we also contribute a learning-based mesh extraction from the estimated UDFs. Extensive evaluations demonstrate that SuperUDF outperforms the state of the arts on several public datasets in terms of both quality and efficiency. Code will be released after accteptance.

翻译：基于无符号距离函数（UDF）的学习型表面重建具有处理开放表面等诸多优势。本文提出SuperUDF——一种利用学习几何先验实现高效训练、并采用新型正则化方法以提升稀疏采样鲁棒性的自监督UDF学习方法。其核心思想受经典局部最优投影（LOP）表面逼近算子的启发：关键洞察在于，若UDF估计准确，三维点应能沿UDF梯度方向局部投影到潜在表面上。基于此，我们设计了若干关于UDF几何的归纳偏置以及预学习的几何先验，以实现高效的UDF估计学习。为增强SuperUDF对稀疏采样的鲁棒性，还提出一种新型正则化损失函数。此外，我们贡献了一种基于学习的方法，用于从估计的UDF中提取网格。大量评估表明，SuperUDF在多个公开数据集上的质量与效率均优于当前最先进方法。代码将在论文接收后开源。