To deal with occlusion is one of the most challenging problems for monocular 6-DOF object pose tracking. In this letter, we propose a novel 6-DOF object pose tracking method which is robust to heavy occlusions. When the tracked object is occluded by another object, instead of trying to detect the occluder, we seek to see through it, as if the occluder doesnt exist. To this end, we propose to combine a learning-based video object segmentation module with an optimization-based pose estimation module in a closed loop. Firstly, a model-guided video object segmentation network is utilized to predict the accurate and full mask of the object (including the occluded part). Secondly, a non-linear 6-DOF pose optimization method is performed with the guidance of the predicted full mask. After solving the current object pose, we render the 3D object model to obtain a refined, model-constrained mask of the current frame, which is then fed back to the segmentation network for processing the next frame, closing the whole loop. Experiments show that the proposed method outperforms the state-of-arts by a large margin for dealing with heavy occlusions, and could handle extreme cases which previous methods would fail.

中文翻译：

---

看穿遮挡物：通过模型引导的视频对象分割实现强大的单目 6-DOF 对象姿态跟踪

处理遮挡是单目 6-DOF 对象姿态跟踪最具挑战性的问题之一。在这封信中，我们提出了一种新颖的 6-DOF 对象姿态跟踪方法，该方法对重度遮挡具有鲁棒性。当被跟踪的物体被另一个物体遮挡时，我们不是试图检测遮挡物，而是试图看穿它，就好像遮挡物不存在一样。为此，我们建议在闭环中将基于学习的视频对象分割模块与基于优化的姿势估计模块相结合。首先，利用模型引导的视频对象分割网络来预测对象（包括被遮挡部分）的准确和完整掩码。其次，在预测的全掩膜的指导下执行非线性6自由度姿态优化方法。求解当前物体位姿后，我们渲染 3D 对象模型以获得当前帧的精细的、模型约束的掩码，然后将其反馈到分割网络以处理下一帧，从而关闭整个循环。实验表明，所提出的方法在处理严重遮挡方面大大优于现有技术，并且可以处理以前方法失败的极端情况。