Abstract
In this paper, we analyze and improve into the recently proposed DeDoDe keypoint detector. We focus our analysis on some key issues. First, we find that DeDoDe keypoints tend to cluster together, which we fix by performing non-max suppression on the target distribution of the detector during training. Second, we address issues related to data augmentation. In particular, the DeDoDe detector is sensitive to large rotations. We fix this by including 90-degree rotations as well as horizontal flips. Finally, the decoupled nature of the DeDoDe detector makes evaluation of downstream usefulness problematic. We fix this by matching the keypoints with a pretrained dense matcher (RoMa) and evaluating two-view pose estimates. We find that the original long training is detrimental to performance, and therefore propose a much shorter training schedule. We integrate all these improvements into our proposed detector DeDoDe v2 and evaluate it with the original DeDoDe descriptor on the MegaDepth-1500 and IMC2022 benchmarks. Our proposed detector significantly increases pose estimation results, notably from 75.9 to 78.3 mAA on the IMC2022 challenge. Code and weights are available at this https URL
Abstract (translated)
在本文中,我们对最近提出的DeDoDe关键点检测器进行了分析和改进。我们重点关注了几个关键问题。首先,我们发现DeDoDe关键点倾向于聚类在一起,这是通过在训练过程中对检测器的目标分布进行非最大抑制来修复的。其次,我们解决了与数据增强相关的问题。特别是,DeDoDe检测器对大旋转敏感。我们通过包括90度旋转和水平翻转来解决这个问题。最后,DeDoDe检测器的解耦性质使得对下游有用性的评估变得复杂。我们通过使用预训练的密集匹配器(RoMa)将关键点匹配,并使用双视图姿态估计来评估。我们发现,原始的长时间训练对性能是有害的,因此我们提出了一个更短的学习计划。我们将所有这些改进集成到我们提出的检测器DeDoDe v2中,并在MegaDepth-1500和IMC2022基准上使用原始DeDoDe描述符进行评估。我们的检测器显著提高了姿态估计结果,特别是从75.9到78.3mAA on the IMC2022 challenge。代码和权重可在此处访问:<https://www.example.com>
URL
https://arxiv.org/abs/2404.08928