发表机构
College of Artificial Intelligence, Zhejiang University（浙江大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现实世界场景数据3D几何不完整问题，提出神经深度场（NDF），将深度估计器视为场景级隐式场解决问题，通过单测试时优化实现，实验表明其在3D场景几何修复中性能优异。
AI 中文摘要
现实世界场景数据的3D几何通常不完整。主流方法使用深度估计器修复缺失结构，但预测结果可能与观测几何不一致，或在分布外数据上不可靠。为解决这些问题，我们提出神经深度场（NDF）。关键见解是深度估计器也可是场景级隐式场。作为估计器，通过学习观测深度数据适应目标域；作为隐式场，拟合现有几何保持一致性。实验表明，NDF在不同场景数据上产生高保真且全局一致的几何，减少跨视图不一致63.3%，提高修复精度23.1%，在3D场景几何修复中达到了当前最优性能。
英文摘要
The 3D geometry of real-world scene data is often incomplete. Mainstream methods use depth estimators to inpaint missing structure. However, their prediction results can be inconsistent with observed geometry, or unreliable on out-of-distribution data. To solve these problems, we propose Neural Depth Field (NDF). Our key insight is that a depth estimator can also be a scene-level implicit field. As an estimator, it adapts to the target domain by learning observed depth data. As an implicit field, it fits the existing geometry to maintain consistency. Under this view, NDF addresses both problems through a single test-time optimization. Experiments show that NDF produces high-fidelity and globally consistent geometry across diverse scene data, ranging from indoor scans to satellite imagery. It reduces cross-view inconsistency by 63.3\% and improves inpainting accuracy by 23.1\%, achieving state-of-the-art performance in 3D scene geometry inpainting. The code is available at: https://github.com/Shadow-Dream/Neural-Depth-Field.
