We present LM-Reloc -- a novel approach for visual relocalization based on direct image alignment. In contrast to prior works that tackle the problem with a feature-based formulation, the proposed method does not rely on feature matching and RANSAC. Hence, the method can utilize not only corners but any region of the image with gradients. In particular, we propose a loss formulation inspired by the classical Levenberg-Marquardt algorithm to train LM-Net. The learned features significantly improve the robustness of direct image alignment, especially for relocalization across different conditions. To further improve the robustness of LM-Net against large image baselines, we propose a pose estimation network, CorrPoseNet, which regresses the relative pose to bootstrap the direct image alignment. Evaluations on the CARLA and Oxford RobotCar relocalization tracking benchmark show that our approach delivers more accurate results than previous state-of-the-art methods while being comparable in terms of robustness.
翻译:我们提出LM-Reloc -- -- 一种基于直接图像对齐的视觉重新定位新颖方法。 与以前以基于地貌的配方来解决这个问题的工程不同, 拟议的方法并不依赖于特征匹配和RANSAC。 因此, 这种方法不仅可以使用角, 还可以使用带有梯度的图像的任何区域。 特别是, 我们提出由古典Levenberg- Marquardt 算法启发的一种损失配方, 用于培训 LM- Net 。 学到的特性大大改善了直接图像匹配的稳健性, 特别是在不同条件下重新定位。 为了进一步提高LM- Net相对于大型图像基线的稳健性, 我们提议了一个配置估算网络 CorrPoseNet, 该网络将相对的态势倒退, 以吸引直接的图像对齐。 对 CARLA 和 Oxford Roban Car 重新定位跟踪基准的评估显示, 我们的方法比以前最先进的方法提供更准确的结果, 同时在坚固性方面可以比较。