# Voxeland：基于证据的不确定性量化的概率式实例感知语义建图

> 原文链接：https://robotics.hellobike.com/papers/2026-07-30-2411-08727
> 频道：papers | 更新日期：2026-07-30 | 标签：arxiv, cs.RO
> 核心摘要：Voxeland将网络预测建模为几何与语义层面的主观意见，增量构建带不确定性的实例感知语义地图，并在SceneNN和ScanNet上验证。

# Voxeland：基于证据的不确定性量化的概率式实例感知语义建图

::: v-pre
> 原文链接：[Voxeland: Probabilistic instance-aware semantic mapping with evidence-based uncertainty quantification](https://arxiv.org/abs/2411.08727)（arXiv 2411.08727 · 发布日期：2026-07-30）

**Voxeland: Probabilistic instance-aware semantic mapping with evidence-based uncertainty quantification**

Voxeland将网络预测建模为几何与语义层面的主观意见，增量构建带不确定性的实例感知语义地图，并在SceneNN和ScanNet上验证。

## 核心要点

- 面向以人为中心环境，过度依赖神经网络预测会使地图易受错误影响。
- Voxeland受证据理论启发，将几何和语义预测视为关于实例的主观意见。
- 框架随时间聚合意见形成证据，并用概率模型量化重建过程的不确定性。
- 方法在SceneNN基准优于现有方法，并在ScanNet上完成定性和定量验证。

**验证范围与局限**：验证范围为公开SceneNN数据集标准基准，以及真实世界ScanNet数据集实验。

## 英文摘要 (Abstract)

Robots in human-centered environments require accurate scene understanding to perform high-level tasks effectively. This understanding can be achieved through instance-aware semantic mapping, which involves reconstructing elements at the level of individual instances. Neural networks, the de facto solution for scene understanding, still face limitations such as overconfident incorrect predictions with out-of-distribution objects or generating inaccurate masks. Placing excessive reliance on these predictions makes the reconstruction susceptible to errors, reducing the robustness of the resulting maps and hampering robot operation. In this work, we propose Voxeland, a probabilistic framework for incrementally building instance-aware semantic maps. Inspired by the Theory of Evidence, Voxeland treats neural network predictions as subjective opinions regarding map instances at both geometric and semantic levels. These opinions are aggregated over time to form evidence, and are formalized through a probabilistic model. This enables us to quantify uncertainty in the reconstruction process, facilitating the identification of map areas requiring improvement (e.g. reobservation or reclassification). As a possible strategy to exploit this uncertainty quantification, we incorporate a Large Vision-Language Model (LVLM) to perform semantic level disambiguation for instances with high uncertainty. Results from the standard benchmarking on the publicly available SceneNN dataset demonstrate that Voxeland outperforms state-of-the-art methods, highlighting the benefits of incorporating and leveraging both instance- and semantic-level uncertainties to enhance reconstruction robustness. This is further validated through qualitative and quantitative experiments conducted on the real-world ScanNet dataset.

作者：Jose-Luis Matez-Bandera, Pepe Ojeda, Javier Monroy, Javier González-Jiménez, José-Raúl Ruiz-Sarmiento
:::

## 原始参考来源 (Sources)

- [arXiv 2411.08727：Voxeland: Probabilistic instance-aware semantic mapping with evidence-based uncertainty quantification](https://arxiv.org/abs/2411.08727)