用不准确的定位标签训练出高精度地图匹配模型
AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels
- 从原始GPS标签中学习，无需真实朝向信息
- 在原始位置周围设置容差区域，提升定位精度
- 利用图像间相对位姿提升训练信号质量
神经地图匹配器可估计图像相对于二维地图的3-自由度姿态。这类模型通常基于大规模地理参考图像数据集进行训练，但其位置和朝向标签常含噪声，影响模型性能。为此，我们提出AutoCompass，一种从不准确的绝对姿态标签中训练神经地图匹配器的监督方法。首先，我们发现朝向标签并非必需：仅使用原始GPS标签训练的模型能自动学习出准确朝向。其次，在原始GPS坐标周围定义容忍区域，可显著提升位置估计精度。第三，若可获得，使用通过SLAM或SfM获取的训练图像间相对位姿作为监督信号，提供更精确的训练依据。在驾驶和自摄基准测试中，AutoCompass始终优于依赖强绝对标签的传统方法。
原文摘要 · Abstract (English)
Neural map matchers estimate an image's 3-DoF pose relative to a 2D map. These models are trained on large-scale datasets of geo-referenced images, whose position and heading labels often contain noise that affects the trained models. To address this, we present AutoCompass, a supervision approach for training neural map matchers from inaccurate absolute pose labels. First, we show that heading labels are unnecessary: trained from raw GPS labels, models learn to predict accurate headings, automatically. Second, defining a tolerance region around raw GPS improves positional accuracy. Third, if available, our supervision uses relative poses between training images, obtained via SLAM or SfM, which provide a more accurate training signal. Across driving and egocentric benchmarks, AutoCompass consistently outperforms counterparts trained with the usual strong reliance on absolute pose labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。