arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2508.02443cs.GRcs.CV
收藏

PRIMU:基于原始体表示的误差与覆盖度的不确定性估计

PRIMU: Uncertainty Estimation for Novel Views in Gaussian Splatting from Primitive-Based Representations of Error and Coverage

Department of Mathematics(数学系);University of Wuppertal(乌珀塔尔大学);Institute of Computer Science(计算机科学研究所);University of Osnabrück(奥斯纳布吕克大学);Centre for Robotics(机器人中心);Queensland University of Technology(昆士兰理工大学)

Thomas Gottwald, Edgar Heinert, Peter Stehr, Chamuditha Jayanga Galappaththige, Matthias Rottmann

AI总结:

PRIMU通过基于原始体的误差和覆盖度表示,实现了高斯点扩散中对新视图不确定性的有效估计,优于现有方法,尤其在深度和前景物体估计上表现突出。

摘要:

我们引入了基于原始体的不确定性表示(PRIMU),一种用于高斯点扩散(GS)的后处理不确定性估计(UE)框架。可靠的UE对于在安全关键领域如机器人学和医学中部署GS至关重要。现有方法通常估计高斯原始体的方差并依赖渲染过程来获得像素级的不确定性。相反,我们从训练视图中构建原始体级别的误差和可见性/覆盖度表示,捕捉可解释的不确定性信息。这些表示通过将视图依赖的训练误差和覆盖度统计投影到原始体上获得。通过渲染这些原始体级别的表示,推断出新视图的不确定性,生成不确定性特征图,通过像素级回归在验证数据上进行聚合。我们分析不确定性特征图和回归模型的组合,以了解它们的相互作用如何影响预测精度和泛化能力。PRIMU还通过直接利用这些不确定性特征图实现了有效的主动视图选择策略。此外,我们研究了将点云分割为前景和背景区域的影响。我们的估计显示与真实误差有很强的相关性,优于最先进的方法,尤其是在深度UE和前景物体方面。最后,我们的回归模型展示了对未见过场景的泛化能力,使无需额外验证数据即可实现UE。

英文摘要:

We introduce Primitive-based Representations of Uncertainty (PRIMU), a post-hoc uncertainty estimation (UE) framework for Gaussian Splatting (GS). Reliable UE is essential for deploying GS in safety-critical domains such as robotics and medicine. Existing approaches typically estimate Gaussian-primitive variances and rely on the rendering process to obtain pixel-wise uncertainties. In contrast, we construct primitive-level representations of error and visibility/coverage from training views, capturing interpretable uncertainty information. These representations are obtained by projecting view-dependent training errors and coverage statistics onto the primitives. Uncertainties for novel views are inferred by rendering these primitive-level representations, producing uncertainty feature maps, which are aggregate through pixel-wise regression on holdout data. We analyze combinations of uncertainty feature maps and regression models to understand how their interactions affect prediction accuracy and generalization. PRIMU also enables an effective active view selection strategy by directly leveraging these uncertainty feature maps. Additionally, we study the effect of separating splatting into foreground and background regions. Our estimates show strong correlations with true errors, outperforming state-of-the-art methods, especially for depth UE and foreground objects. Finally, our regression models show generalization capabilities to unseen scenes, enabling UE without additional holdout data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑