提出PH-Dropout，实现预训练神经视图合成模型的实时精准不确定性估计。
PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis
- 后处理式随机丢弃，无需重新训练即可估算不确定性。
- 在NeRF和GS模型上实现亚秒级推理，精度媲美重训练方法。
- 适合需要可靠误差评估的工业级视图合成系统部署。
基于神经辐射场（NeRF）和高斯点阵（GS）的视图合成在还原真实场景方面表现出色，但缺乏高效准确的先验不确定性量化（UQ）方法。现有NeRF方法或引入显著计算开销（如训练时间增加10倍或重复训练10次），或仅适用于特定不确定性场景与模型。值得注意的是，GS模型尚无系统性方法实现全面的先验不确定性量化。该能力对提升神经视图合成的鲁棒性与可扩展性至关重要，支持主动模型更新、误差估计及基于不确定性的规模化集成建模。本文从函数逼近视角重新审视NeRF与GS方法，揭示3D表示学习中的关键差异与联系。基于此，我们提出首个可在预训练模型上直接运行的实时、精准先验不确定性估计方法——PH-Dropout（后处理丢弃）。大量实验验证了理论发现，并证明了其有效性。
原文摘要 · Abstract (English)
View synthesis using Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) has demonstrated impressive fidelity in rendering real-world scenarios. However, practical methods for accurate and efficient epistemic Uncertainty Quantification (UQ) in view synthesis are lacking. Existing approaches for NeRF either introduce significant computational overhead (e.g., ``10x increase in training time" or ``10x repeated training") or are limited to specific uncertainty conditions or models. Notably, GS models lack any systematic approach for comprehensive epistemic UQ. This capability is crucial for improving the robustness and scalability of neural view synthesis, enabling active model updates, error estimation, and scalable ensemble modeling based on uncertainty. In this paper, we revisit NeRF and GS-based methods from a function approximation perspective, identifying key differences and connections in 3D representation learning. Building on these insights, we introduce PH-Dropout (Post hoc Dropout), the first real-time and accurate method for epistemic uncertainty estimation that operates directly on pre-trained NeRF and GS models. Extensive evaluations validate our theoretical findings and demonstrate the effectiveness of PH-Dropout.
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。