Refractive Structure-from-Motion Through a Flat Refractive Interface
Refractive Structure-from-Motion Through a Flat Refractive Interface
复制标题
DOI：
10.1109/iccv.2017.568
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
F. Chadebecq;F. Vasconcelos;G. Dwyer;Rene M. Lacher;S. Ourselin;Tom Kamiel Magda Vercauteren;D. Stoyanov-D.-S
中科院分区：
文献类型：
--
作者：
F. Chadebecq;F. Vasconcelos;G. Dwyer;Rene M. Lacher;S. Ourselin;Tom Kamiel Magda Vercauteren;D. Stoyanov-D.-S
从水下图像中恢复三维场景几何形状涉及到运动折射结构（RSfM）问题，其中由不同传播介质之间的界面处的光折射引起的图像失真使单视点假设失效。在RSfM中直接使用针孔相机模型会导致相机位姿估计不准确，从而导致漂移。RSfM方法已针对厚玻璃界面的情况进行了深入研究，该界面假设相机和所观察场景之间有两个折射界面。另一方面，当相机透镜与水直接接触时，仅存在一个折射界面。通过明确考虑折射界面，我们开发了一个简洁的推导的折射基本矩阵的形式的轴向相机的广义核线约束。我们使用折射基本矩阵来细化通过假设针孔模型获得的初始姿态估计。这种策略使我们能够鲁棒地估计水下相机的姿态，而其他方法对噪声的敏感性很差。我们还制定了一个新的四视图约束，强制执行相机姿态一致性沿着的视频，这使我们一个新的RSfM框架。为了验证，我们使用合成数据来显示我们的方法的数值特性，我们提供了真实的数据的结果，以证明在实验室设置和内窥镜检查中的应用的性能。
Recovering 3D scene geometry from underwater images involves the Refractive Structure-from-Motion (RSfM) problem, where the image distortions caused by light refraction at the interface between different propagation media invalidates the single view point assumption. Direct use of the pinhole camera model in RSfM leads to inaccurate camera pose estimation and consequently drift. RSfM methods have been thoroughly studied for the case of a thick glass interface that assumes two refractive interfaces between the camera and the viewed scene. On the other hand, when the camera lens is in direct contact with the water, there is only one refractive interface. By explicitly considering a refractive interface, we develop a succinct derivation of the refractive fundamental matrix in the form of the generalised epipolar constraint for an axial camera. We use the refractive fundamental matrix to refine initial pose estimates obtained by assuming the pinhole model. This strategy allows us to robustly estimate underwater camera poses, where other methods suffer from poor noise-sensitivity. We also formulate a new four view constraint enforcing camera pose consistency along a video which leads us to a novel RSfM framework. For validation we use synthetic data to show the numerical properties of our method and we provide results on real data to demonstrate performance within laboratory settings and for applications in endoscopy.