将深度估计器视为隐式场，实现更一致的3D场景补全。
Depth Estimators Are Implicit Neural Fields for 3D Scene Geometry Inpainting and Reconstruction
- 把深度估计器看作全局隐式场，统一建模与补全
- 跨视图不一致性降低63.3%，补全精度提升23.1%
- 适用于室内扫描到卫星图像的多种场景
真实世界场景数据的3D几何信息常不完整。主流方法使用深度估计器补全缺失结构，但其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。为此，我们提出神经深度场（NDF）。核心思想是：深度估计器本身可作为场景级隐式场。作为估计器，它通过学习观测深度数据适应目标域；作为隐式场，它拟合已有几何以保持一致性。在此框架下，NDF通过一次测试时优化解决两类问题。实验表明，NDF在从室内扫描到卫星影像的多样化场景数据中均生成高保真、全局一致的几何结构，跨视图不一致性降低63.3%，补全精度提升23.1%，在3D场景几何补全任务上达到最先进水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。