无需训练即可量化辐射场不确定性，提升视角选择与建图效果。
WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields
- 通过跨视角反向投影，利用一致性判断新视角的不确定性
- 在主动视角选择和建图任务中优于现有定制化方法
- 无需训练，适配任意辐射场模型，通用性强
我们提出WarpRF，一种无需训练的通用框架，用于量化辐射场的不确定性。基于精确模型在不同视角间应保持光度与几何一致性的假设，WarpRF通过跨视角反向映射，将可靠渲染结果投影至未见视角，并测量其与该视角直接渲染图像的一致性来量化不确定性。该方法简单且计算成本低，不依赖任何训练，可自由应用于任意辐射场实现。WarpRF在不确定性量化及下游任务（如主动视角选择、主动建图）中表现优异，超越所有针对特定框架设计的现有方法。
原文摘要 · Abstract (English)
We introduce WarpRF, a training-free general-purpose framework for quantifying the uncertainty of radiance fields. Built upon the assumption that photometric and geometric consistency should hold among images rendered by an accurate model, WarpRF quantifies its underlying uncertainty from an unseen point of view by leveraging backward warping across viewpoints, projecting reliable renderings to the unseen viewpoint and measuring the consistency with images rendered there. WarpRF is simple and inexpensive, does not require any training, and can be applied to any radiance field implementation for free. WarpRF excels at both uncertainty quantification and downstream tasks, e.g., active view selection and active mapping, outperforming any existing method tailored to specific frameworks.
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。