为3D重建中的不确定性源分类并提出量化方法，提升模型对噪声和误差的感知能力。
Sources of Uncertainty in 3D Scene Reconstruction
- 构建不确定性分类体系，涵盖噪声、遮挡、异常值等关键来源
- 在NeRF与GS基础上引入不确定性输出学习与集成方法
- 实验证明该方法能有效捕捉重建对输入误差的敏感性
3D场景重建过程易受真实场景中多种不确定性因素影响。尽管神经辐射场（NeRF）和3D高斯泼溅（GS）能实现高保真渲染，但缺乏直接处理或量化由噪声、遮挡、混杂异常值及相机位姿不精确等引起的不确定性的机制。本文提出一个针对这些方法内在不确定性来源的分类体系，并扩展基于NeRF与GS的方法，引入不确定性输出学习与集成技术，通过实证研究评估其对重建敏感性的捕捉能力。研究强调，在设计面向不确定性的NeRF/GS方法时，需全面考虑各类不确定性因素。
原文摘要 · Abstract (English)
The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) achieve high-fidelity rendering, they lack built-in mechanisms to directly address or quantify uncertainties arising from the presence of noise, occlusions, confounding outliers, and imprecise camera pose inputs. In this paper, we introduce a taxonomy that categorizes different sources of uncertainty inherent in these methods. Moreover, we extend NeRF- and GS-based methods with uncertainty estimation techniques, including learning uncertainty outputs and ensembles, and perform an empirical study to assess their ability to capture the sensitivity of the reconstruction. Our study highlights the need for addressing various uncertainty aspects when designing NeRF/GS-based methods for uncertainty-aware 3D reconstruction.
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。