CoLoR：大规模视觉定位中场景坐标回归的关键所在
CoLoR: The Devil is in Scene Coordinate Regression for Large-Scale Visual Localization
针对大场景下稀疏共视与局部外观歧义问题，提出将场景点划分为多视图/单视图集的两阶段自举监督，以及统一全局与局部特征的图像级/像素级多粒度检索特征，可直接用于提升基于 SCR 的大规模视觉定位精度，同时保持紧凑地图。
原文依据 we propose a multi-granularity retrieval feature, which unifies the conventional global and local features as retrieval-oriented representations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论场景坐标回归（SCR）已成为一种内存高效的视觉定位范式。尽管 SCR 在小规模场景中表现出与经典基于特征匹配的方法相当的性能，但在大规模环境中却始终表现不佳。大规模定位受制于两个挑战：稀疏共视与局部外观歧义。在本工作中，我们提出 CoLoR，一种专为大规模 SCR 设计的新训练框架。首先，我们显式且高效地将场景点划分为多视图集与单视图集，并引入两阶段自举范式，为所有点提供完整且强力的监督。其次，我们提出一种多粒度检索特征，将传统的全局特征与局部特征分别统一为图像级与像素级的面向检索的表示，以增强特征一致性。我们的方法在多个具有挑战性的大规模数据集上取得最优性能，并在保持紧凑地图尺寸的同时显著缩小了与经典基于特征匹配的方法之间的精度差距。
英文原文摘要 1138 字符
Scene Coordinate Regression (SCR) has emerged as a memory-efficient paradigm for visual localization. While SCR has demonstrated performance comparable to classic feature matching based approaches in small-scale scenes, it has consistently underperformed in large-scale environments. Large-scale localization is hampered by two challenges: sparse co-visibility and local appearance ambiguity. In this work, we propose CoLoR, a novel training framework tailored for large-scale SCR. First, we explicitly and efficiently partition scene points into multi-view and single-view sets and introduce a two-stage bootstrapping paradigm to provide complete and strong supervision for all points. Second, we propose a multi-granularity retrieval feature, which unifies the conventional global and local features as retrieval-oriented representations at the image and pixel levels, respectively, to enforce feature consistency. Our method achieves state-of-the-art performance on multiple challenging large-scale datasets and significantly narrows the accuracy gap with classical feature matching based approaches while retaining a compact map size.