通过可变可见性场提升3D高斯点云的不确定性建模与主动测绘效率。
Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
- 基于球谐函数建模粒子在训练视角下的各向异性可见性。
- 实现200帧/秒实时不确定性估计，显著提升合成视图精度。
- 适用于新旧方法增强，尤其适合动态环境主动建图场景。
我们提出高斯点云各向异性可见性场（GAVIS），一种用于3DGS中不确定性量化与主动建图的新框架。核心洞察是：从训练视角未观测到的区域，其3DGS预测结果不可靠。为此，我们提出一种原理严谨且高效的3DGS可见性场量化方法，定义为每个粒子相对于训练视角的各向异性可见性，并用球谐函数表示。该可见性场被整合进基于贝叶斯网络的不确定性感知3DGS光栅化器中，实现实时（200 FPS）合成视图的不确定性量化。在此基础上，构建最大信息增益框架实现主动建图。在多样环境中的大量实验表明，GAVIS在准确性和效率上均显著优于现有方法。此外，本方法还可作为后处理手段提升已有方法性能。
原文摘要 · Abstract (English)
We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches.
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。