论文标题
重复使用您的功能：统一检索和功能 - 金属对齐
Reuse your features: unifying retrieval and feature-metric alignment
论文作者
论文摘要
我们提出了一条紧凑的管道，以统一视觉定位的所有步骤：图像检索，候选人重新排列和初始姿势估计以及相机姿势改进。我们的关键假设是，用于这些单个任务的深度特征具有共同的特征，因此我们应该在管道的所有过程中重复使用它们。我们的DRAN（深度检索和图像对齐网络）能够提取全局描述符，以进行有效的图像检索，使用中间层次结构特征来重新排列检索列表并产生初始姿势猜测，最终通过基于学识渊博的多尺度密集的深度多尺度的特征 - 量优化来完善。 Dran是第一个能够为视觉定位三个步骤生成功能的单个网络。与使用多个网络相比，Dran在挑战性的条件下，在富有挑战性的条件下，在富有挑战性的条件下实现了竞争性能，优于其他统一方法，并消耗较低的计算和内存成本。代码和模型将在https://github.com/jmorlana/dran上公开获取。
We propose a compact pipeline to unify all the steps of Visual Localization: image retrieval, candidate re-ranking and initial pose estimation, and camera pose refinement. Our key assumption is that the deep features used for these individual tasks share common characteristics, so we should reuse them in all the procedures of the pipeline. Our DRAN (Deep Retrieval and image Alignment Network) is able to extract global descriptors for efficient image retrieval, use intermediate hierarchical features to re-rank the retrieval list and produce an initial pose guess, which is finally refined by means of a feature-metric optimization based on learned deep multi-scale dense features. DRAN is the first single network able to produce the features for the three steps of visual localization. DRAN achieves competitive performance in terms of robustness and accuracy under challenging conditions in public benchmarks, outperforming other unified approaches and consuming lower computational and memory cost than its counterparts using multiple networks. Code and models will be publicly available at https://github.com/jmorlana/DRAN.
