[论文解读] Introduction to Camera Pose Estimation with Deep Learning

Yoli Shavit, Ron Ferens|arXiv (Cornell University)|Jul 8, 2019

Robotics and Sensor-Based Localization参考文献 57被引用 51

一句话总结

对从 RGB 图像回归绝对相机姿态的深度学习方法进行综述，包括方法分类、横向对比、可重复性笔记和未来方向。

ABSTRACT

Over the last two decades, deep learning has transformed the field of computer vision. Deep convolutional networks were successfully applied to learn different vision tasks such as image classification, image segmentation, object detection and many more. By transferring the knowledge learned by deep models on large generic datasets, researchers were further able to create fine-tuned models for other more specific tasks. Recently this idea was applied for regressing the absolute camera pose from an RGB image. Although the resulting accuracy was sub-optimal, compared to classic feature-based solutions, this effort led to a surge of learning-based pose estimation methods. Here, we review deep learning approaches for camera pose estimation. We describe key methods in the field and identify trends aiming at improving the original deep pose regression solution. We further provide an extensive cross-comparison of existing learning-based pose estimators, together with practical notes on their execution for reproducibility purposes. Finally, we discuss emerging solutions and potential future research directions.

研究动机与目标

• 在早期结果不理想之后，推动基于学习的相机姿态估计研究。
• 总结通过 RGB 图像回归绝对相机姿态的关键深度学习方法。
• 提供现有基于学习的姿态估计器的横向比较。
• 提供有助于提高可重复性并指导未来研究的实践性提示。

提出的方法

• 评述并综合用于相机姿态估计的深度学习方法。
• 描述关键方法并识别提升姿态回归性能的趋势。
• 提供现有基于学习的估计器的广泛横向比较。
• 讨论可重复性与实现的实际考虑因素。

实验结果

研究问题

• RQ1 用于从 RGB 图像进行相机姿态估计的主要深度学习方法有哪些？
• RQ2 不同的基于学习的姿态估计器在性能、优点和缺点方面的比较如何？
• RQ3 哪些实际因素影响姿态估计方法的可重复性和部署？
• RQ4 为深度学习的姿态估计识别出的未来方向和新兴解决方案有哪些。

主要发现

• 本论文回顾用于相机姿态估计的深度学习方法，并讨论了朝着改进原始回归式解决方案的趋势。
• 它提供了现有基于学习的姿态估计器的广泛横向比较。
• 它提供了有助于提升可重复性的执行方法的实际笔记。
• 它讨论了新兴的解决方案和潜在的未来研究方向。