将3D高斯点阵中的语义映射升级为可量化不确定性的概率模型。
Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splatting
- 用共轭先验在3D椭球上做概率语义更新，同时输出均值与方差。
- 提出概率光栅化，每像素输出带置信度的分割结果。
- 适合需要安全验证的机器人场景，如自动驾驶、无人机导航。
本文提出一种新算法，在3D高斯点阵（3D-GS）中实现语义地图的概率更新与光栅化。尽管已有方法尝试在3D-GS中学习特征光栅化以增强场景理解，但3D-GS可能无声失效，这对安全关键型机器人应用构成挑战。为此，我们提出将连续语义建模从体素扩展至椭球，结合3D-GS的精确结构与概率地图的不确定性量化能力。给定一组图像，算法直接在3D椭球上进行概率语义更新，利用共轭先验获得期望与方差。同时提出概率光栅化方法，返回带有可量化不确定性的像素级分割预测。通过与基于体素的概率方法对比，验证了向3D椭球扩展的有效性，并对不确定性量化与时间平滑进行了消融实验。
原文摘要 · Abstract (English)
In this paper, we present a novel algorithm for probabilistically updating and rasterizing semantic maps within 3D Gaussian Splatting (3D-GS). Although previous methods have introduced algorithms which learn to rasterize features in 3D-GS for enhanced scene understanding, 3D-GS can fail without warning which presents a challenge for safety-critical robotic applications. To address this gap, we propose a method which advances the literature of continuous semantic mapping from voxels to ellipsoids, combining the precise structure of 3D-GS with the ability to quantify uncertainty of probabilistic robotic maps. Given a set of images, our algorithm performs a probabilistic semantic update directly on the 3D ellipsoids to obtain an expectation and variance through the use of conjugate priors. We also propose a probabilistic rasterization which returns per-pixel segmentation predictions with quantifiable uncertainty. We compare our method with similar probabilistic voxel-based methods to verify our extension to 3D ellipsoids, and perform ablation studies on uncertainty quantification and temporal smoothing.
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。