OpenFusion++：一个开放词汇的实时场景理解系统
OpenFusion++: An Open-vocabulary Real-time Scene Understanding System
AI总结：
提出基于TSDF的实时3D语义几何重建系统OpenFusion++，通过融合基础模型置信度图优化点云、自适应缓存动态更新语义标签及双路径编码框架处理复杂查询，在多个数据集上显著提升了语义准确性和查询响应性。
摘要：
实时开放词汇场景理解对于视觉语言导航、具身智能和增强现实等应用中的高效3D感知至关重要。然而，现有方法存在实例分割不精确、静态语义更新以及对复杂查询处理能力有限的问题。为了解决这些问题，我们提出了OpenFusion++，一个基于TSDF的实时3D语义几何重建系统。我们的方法通过融合基础模型的置信度图来优化3D点云，通过基于实例面积的自适应缓存动态更新全局语义标签，并采用将对象属性与环境上下文相结合的双路径编码框架以实现精确的查询响应。在ICL、Replica、ScanNet和ScanNet++数据集上的实验表明，OpenFusion++在语义准确性和查询响应性方面均显著优于基线。
英文摘要：
Real-time open-vocabulary scene understanding is essential for efficient 3D perception in applications such as vision-language navigation, embodied intelligence, and augmented reality. However, existing methods suffer from imprecise instance segmentation, static semantic updates, and limited handling of complex queries. To address these issues, we present OpenFusion++, a TSDF-based real-time 3D semantic-geometric reconstruction system. Our approach refines 3D point clouds by fusing confidence maps from foundational models, dynamically updates global semantic labels via an adaptive cache based on instance area, and employs a dual-path encoding framework that integrates object attributes with environmental context for precise query responses. Experiments on the ICL, Replica, ScanNet, and ScanNet++ datasets demonstrate that OpenFusion++ significantly outperforms the baseline in both semantic accuracy and query responsiveness.
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。
