ReLoc：重新思考用于鲁棒室外基于LiDAR定位的场景坐标回归架构
ReLoc: Rethinking Scene Coordinate Regression Architecture for Robust Outdoor LiDAR-based Localization
- Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ReLoc通过重新设计全局嵌入和引入注意力局部特征增强，解决了SCR在室外LiDAR定位中细粒度区分不足和噪声传播问题，实现最先进精度并保持实时性能。
AI中文摘要：
场景坐标回归（SCR）近期已成为基于LiDAR定位的一种有前景的方法，无需显式3D地图即可实现精确定位。尽管有效，现有SCR方法依赖基于场景分类的全局嵌入，难以在邻近位置之间提供细粒度区分。此外，它们在训练期间对局部特征进行均匀采样，赋予所有点同等重要性，从而无意中传播来自动态物体或不稳定区域的特征，可能降低训练稳定性。在本文中，我们提出ReLoc，一种改进的SCR架构，可有效解决这些局限。首先，我们重新设计全局嵌入模块，将可学习的上下文令牌与特征聚合器结合，以捕获更丰富且更具区分性的场景上下文。其次，我们引入基于注意力的局部特征增强模块，以减轻噪声局部特征的影响，同时鼓励上下文一致的结构，产生更鲁棒的局部特征表示。在两个大规模室外数据集上的实验结果表明，我们的方法在先前基于SCR的方法中达到了最先进的精度，同时保持实时推理性能。
英文摘要：
Scene Coordinate Regression (SCR) has recently emerged as a promising approach for LiDAR-based localization, achieving accurate localization without requiring an explicit 3D map. Despite their effectiveness, existing SCR methods rely on scene classification-based global embedding that struggles to provide fine-grained discrimination among nearby locations. Moreover, their reliance on uniform sampling of local features during training assigns equal importance to all points, thereby inadvertently propagating features from dynamic objects or unstable regions and potentially degrading training stability. In this paper, we present ReLoc, a revamped SCR architecture that can effectively address these limitations. First, we redesign the global embedding module by combining learnable context tokens with a feature aggregator to capture richer and more discriminative scene context. Second, we introduce an attention-based local feature enhancement module to mitigate the impact of noisy local features while encouraging context-consistent structures, yielding more robust local feature representations. Experimental results on two large-scale outdoor datasets demonstrate that our approach achieves state-of-the-art accuracy over previous SCR-based methods while maintaining real-time inference performance.
