基本要素：设计简单、有效的开放词汇场景图
The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs
AI总结：
本文通过研究图像预处理、特征融合与特征选择，提出简单高效的开放词汇3D场景图框架，在保持SOTA分类准确率的同时将计算量降低三倍。
摘要：
3D开放词汇场景图方法是具身智能体一种很有前景的地图表示，然而许多现有方法计算成本高昂。本文重新审视以往工作确立的关键设计选择，以同时优化效率与性能。我们提出一个通用场景图框架，并开展三项研究，分别聚焦图像预处理、特征融合和特征选择。研究发现，常用图像预处理技术带来的性能提升极小，却会使计算量增加至三倍（以每个对象视图为基准）。我们还表明，在不同视图之间平均特征标签会显著降低性能。我们研究了可提升性能且不增加不必要计算成本的替代特征选择策略。基于这些发现，我们提出一种计算均衡的方法，利用逐对象特征进行3D点云分割。该方法达到与最先进水平相当的分类准确率，同时将计算量减少三倍。
英文摘要：
3D open-vocabulary scene graph methods are a promising map representation for embodied agents, however many current approaches are computationally expensive. In this paper, we reexamine the critical design choices established in previous works to optimize both efficiency and performance. We propose a general scene graph framework and conduct three studies that focus on image pre-processing, feature fusion, and feature selection. Our findings reveal that commonly used image pre-processing techniques provide minimal performance improvement while tripling computation (on a per object view basis). We also show that averaging feature labels across different views significantly degrades performance. We study alternative feature selection strategies that enhance performance without adding unnecessary computational costs. Based on our findings, we introduce a computationally balanced approach for 3D point cloud segmentation with per-object features. The approach matches state-of-the-art classification accuracy while achieving a threefold reduction in computation.
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。
