从3D高斯泼溅中蒸馏无符号距离函数用于表面重建
Distilling Unsigned Distance Function for Surface Reconstruction from 3D Gaussian Splatting
将基于合成代数曲面训练的 patch 级 UDF 先验蒸馏到 3D 高斯优化中，为开放表面重建提供近表面监督，可复用于其他隐式场与显式表示结合的几何学习任务。
原文依据 distilling a patch-based UDF prior, trained on synthetic ground truth algebraic surfaces with closed form expressions, into a lightweight student UDF inside Gaussian optimization process
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无符号距离场（UDF）非常适合表示开放表面，但从多视图图像中学习它们具有挑战性，因为在大多数情况下没有真值表面可供监督，并且 UDF 的梯度在底层表面上未定义。先前的方法使用全局目标优化 UDF，并应用基于梯度的先验，忽略了目标表面上查询的不可微性，导致训练不稳定和精细细节过度平滑。我们通过将基于块（patch）的 UDF 先验蒸馏到高斯优化过程中的轻量级学生 UDF 中来解决这些问题，该先验在具有闭式表达式的合成真值代数曲面上训练。我们设计了带限知识蒸馏策略，利用预训练的基于块的 UDF 预测器提供可靠的近表面 UDF 监督，从而实现稳定的学生训练并恢复高频几何细节。此外，我们引入了可见性和几何感知的置信度加权来调节教师的影响，进一步引导学生朝向模糊或弱约束区域中的准确表面。在各种数据集上的大量实验表明，与现有的基于 UDF 和 SDF 的方法相比，我们的方法在保持有竞争力的效率的同时，持续提高了重建精度。
英文原文摘要 1380 字符
Unsigned distance fields (UDFs) are well suited for representing open surfaces, but learning them from multi-view images is challenging because ground-truth surfaces are unavailable for supervision in most cases and the gradient of a UDF is undefined on the underlying surface. Prior methods optimize UDFs with global objectives and apply gradient-based priors ignoring the non-differentiability for queries on the target surface, which leads to unstable training and over-smoothing on fine details. We address these issues by distilling a patch-based UDF prior, trained on synthetic ground truth algebraic surfaces with closed form expressions, into a lightweight student UDF inside Gaussian optimization process. We design band-limited knowledge distillation strategy that leverages a pretrained patch-based UDF predictor to provide reliable near-surface UDF supervision, enabling stable student training and the recovery of high-frequency geometric details. In addition, we introduce a visibility- and geometry-aware confidence weighting that modulates teacher influence, further steering the student toward accurate surfaces in ambiguous or weakly constrained regions. Extensive experiments on various datasets demonstrate that our approach consistently improves reconstruction accuracy while maintaining competitive efficiency compared to existing UDF- and SDF-based methods.