让神经辐射场同时量化两种不确定性，提升三维建模可信度。
Evidential Neural Radiance Fields
- 用证据理论统一建模观测与认知不确定性
- 单次前向传播即得双类不确定性估计，不降渲染质量
- 在三个基准上表现领先，适合高安全场景应用
理解不确定性来源是实现可信三维场景建模的基础。尽管神经辐射场（NeRFs）在场景重建和新视角合成方面取得显著成果，但缺乏不确定性估计严重限制其在安全关键场景中的部署。现有方法无法分别捕捉偶然性与认知性不确定性；即便有方法能分别量化，也常以牺牲渲染质量或带来巨大计算开销为代价。为此，本文提出证据神经辐射场（Evidential NeRF），一种可无缝融入NeRF渲染过程的概率方法，支持通过一次前向传播直接量化两类不确定性。我们在三个标准化基准上对比多种不确定性量化方法，结果表明该方法在场景重建保真度和不确定性估计质量上均达当前最优水平。代码已开源：https://github.com/KerryDRX/EvidentialNeRF。
原文摘要 · Abstract (English)
Understanding sources of uncertainty is fundamental to trustworthy three-dimensional scene modeling. While recent advances in neural radiance fields (NeRFs) achieve impressive accuracy in scene reconstruction and novel view synthesis, the lack of uncertainty estimation significantly limits their deployment in safety-critical settings. Existing uncertainty quantification methods for NeRFs fail to separately capture both aleatoric and epistemic uncertainties. Among those that do quantify one or the other, many of them either compromise rendering quality or incur significant computational overhead to obtain uncertainty estimates. To address these issues, we introduce Evidential Neural Radiance Fields, a probabilistic approach that seamlessly integrates with the NeRF rendering process, enabling direct quantification of both aleatoric and epistemic uncertainties from a single forward pass. We compare multiple uncertainty quantification methods on three standardized benchmarks, where our approach demonstrates state-of-the-art scene reconstruction fidelity and uncertainty estimation quality. Code is available at https://github.com/KerryDRX/EvidentialNeRF.
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。