具有开放词汇理解的紧凑对象级表示用于室内视觉重定位
Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization
AI总结：
提出OpenReLoc系统，利用基础模型实现多模态开放词汇语义匹配、基于DIOU的参考帧选择和双路径2D ICP损失，仅用对象单元实现室内视觉重定位，提升可解释性和准确性。
摘要：
室内视觉重定位在空间和具身AI应用中扮演关键角色。然而，先前研究主要致力于低级视觉方案，难以感知场景语义和组成，限制了可解释性和适用性。本文探索如何将场景中的丰富对象信息（包括语义、布局和几何）组织成结构化地图表示，从而仅利用对象单元驱动相机重定位任务。为此，我们提出OpenReLoc，一种提供场景理解和精确位姿估计能力的相机重定位系统。利用最新基础模型，我们首先引入多模态机制整合开放词汇语义知识，以实现有效的2D-3D对象匹配。此外，我们设计面向对象的参考帧作为位置先验，并基于距离交并比（DIOU）的参考帧选择策略，使其可扩展到大规模场景。同时，为确保稳定精确的位姿优化，我们提出由对象形状引导的双路径2D迭代最近像素损失。实验结果表明，OpenReLoc在多个数据集上实现了优越的重定位召回率和精度。源代码将在接收后发布。
英文摘要：
Indoor visual relocalization plays a critical role in emerging spatial and embodied AI applications. However, prior research was predominantly devoted to low-level vision schemes, struggling to perceive scene semantics and compositions, which limits both interpretability and applicability. In this paper, we explore the issue of how to organize rich object information in a scene, including semantics, layout, and geometry, into a structured map representation, thereby utilizing object units exclusively to drive the camera relocalization task. To this end, we propose OpenReLoc, a camera relocalization system designed to provide scene understanding and accurate pose estimation capabilities. Leveraging recent foundation models, we first introduce a multi-modal mechanism to integrate open-vocabulary semantic knowledge for effective 2D-3D object matching. Additionally, we design object-oriented reference frames as position priors, paired with a reference frame selection strategy based on the Distance-IoU (DIOU), enabling extension to scalable scenes. Moreover, to ensure stable and accurate pose optimization, we also propose a dual-path 2D Iterative Closest Pixel loss guided by object shape. Experimental results demonstrate that OpenReLoc achieves superior relocalization recall and accuracy across various datasets. Our source code will be released upon acceptance.
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。
