当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Insights on Evaluation of Camera Re-localization Using Relative Pose Regression
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-09-23 , DOI: arxiv-2009.11342
Amir Shalev (1,2), Omer Achrack (2), Brian Fulkerson, and Ben-Zion Bobrovsky (1) ((1) Tel-Aviv-University, (2) Intel)

We consider the problem of relative pose regression in visual relocalization. Recently, several promising approaches have emerged in this area. We claim that even though they demonstrate on the same datasets using the same split to train and test, a faithful comparison between them was not available since on currently used evaluation metric, some approaches might perform favorably, while in reality performing worse. We reveal a tradeoff between accuracy and the 3D volume of the regressed subspace. We believe that unlike other relocalization approaches, in the case of relative pose regression, the regressed subspace 3D volume is less dependent on the scene and more affect by the method used to score the overlap, which determined how closely sampled viewpoints are. We propose three new metrics to remedy the issue mentioned above. The proposed metrics incorporate statistics about the regression subspace volume. We also propose a new pose regression network that serves as a new baseline for this task. We compare the performance of our trained model on Microsoft 7-Scenes and Cambridge Landmarks datasets both with the standard metrics and the newly proposed metrics and adjust the overlap score to reveal the tradeoff between the subspace and performance. The results show that the proposed metrics are more robust to different overlap threshold than the conventional approaches. Finally, we show that our network generalizes well, specifically, training on a single scene leads to little loss of performance on the other scenes.

中文翻译:

使用相对姿态回归评估相机重新定位的见解

我们考虑视觉重定位中的相对姿态回归问题。最近,该领域出现了几种有前景的方法。我们声称,即使他们使用相同的拆分来训练和测试在相同的数据集上进行演示,也无法在它们之间进行忠实的比较,因为在当前使用的评估指标上,某些方法可能表现良好,而实际上表现更差。我们揭示了回归子空间的准确性和 3D 体积之间的权衡。我们认为,与其他重定位方法不同,在相对姿态回归的情况下,回归子空间 3D 体积对场景的依赖性较小,而更多地受用于对重叠进行评分的方法的影响,这决定了采样视点的紧密程度。我们提出了三个新指标来解决上述问题。建议的指标包含有关回归子空间体积的统计数据。我们还提出了一个新的姿势回归网络,作为该任务的新基线。我们将经过训练的模型在 Microsoft 7-Scenes 和 Cambridge Landmarks 数据集上的性能与标准指标和新提出的指标进行比较,并调整重叠分数以揭示子空间和性能之间的权衡。结果表明,与传统方法相比,所提出的度量对不同的重叠阈值具有更强的鲁棒性。最后,我们表明我们的网络泛化能力很好,特别是在单个场景上的训练导致其他场景的性能损失很小。我们将经过训练的模型在 Microsoft 7-Scenes 和 Cambridge Landmarks 数据集上的性能与标准指标和新提出的指标进行比较,并调整重叠分数以揭示子空间和性能之间的权衡。结果表明,与传统方法相比,所提出的度量对不同的重叠阈值具有更强的鲁棒性。最后,我们表明我们的网络泛化能力很好,特别是在单个场景上的训练导致其他场景的性能损失很小。我们将经过训练的模型在 Microsoft 7-Scenes 和 Cambridge Landmarks 数据集上的性能与标准指标和新提出的指标进行比较,并调整重叠分数以揭示子空间和性能之间的权衡。结果表明,与传统方法相比,所提出的度量对不同的重叠阈值具有更强的鲁棒性。最后,我们表明我们的网络泛化能力很好,特别是在单个场景上的训练导致其他场景的性能损失很小。结果表明,与传统方法相比,所提出的度量对不同的重叠阈值具有更强的鲁棒性。最后,我们表明我们的网络泛化能力很好,特别是在单个场景上的训练导致其他场景的性能损失很小。结果表明,与传统方法相比,所提出的度量对不同的重叠阈值具有更强的鲁棒性。最后,我们表明我们的网络泛化能力很好,特别是在单个场景上的训练导致其他场景的性能损失很小。
更新日期:2020-09-25
down
wechat
bug