Most recent 6D object pose methods use 2D optical flow to refine their results. However, the general optical flow methods typically do not consider the target's 3D shape information during matching, making them less effective in 6D object pose estimation. In this work, we propose a shape-constraint recurrent matching framework for 6D object pose estimation. We first compute a pose-induced flow based on the displacement of 2D reprojection between the initial pose and the currently estimated pose, which embeds the target's 3D shape implicitly. Then we use this pose-induced flow to construct the correlation map for the following matching iterations, which reduces the matching space significantly and is much easier to learn. Furthermore, we use networks to learn the object pose based on the current estimated flow, which facilitates the computation of the pose-induced flow for the next iteration and yields an end-to-end system for object pose. Finally, we optimize the optical flow and object pose simultaneously in a recurrent manner. We evaluate our method on three challenging 6D object pose datasets and show that it outperforms the state of the art significantly in both accuracy and efficiency.

翻译：最近的大多数6D物体姿态方法利用二维光流来优化结果。然而，通用光流方法通常在匹配过程中不考虑目标的3D形状信息，导致其在6D物体姿态估计中效果欠佳。本文提出了一种形状约束循环匹配框架，用于6D物体姿态估计。我们首先基于初始姿态与当前估计姿态之间的二维重投影位移，计算姿态诱导流，该流隐式嵌入目标的3D形状信息。接着利用该姿态诱导流构建后续匹配迭代的相关性图，显著缩小匹配空间，且更易于学习。此外，我们采用基于当前估计流来学习物体姿态的网络，从而促进下一次迭代中姿态诱导流的计算，构建端到端的物体姿态系统。最终，我们通过循环方式同时优化光流与物体姿态。在三个具有挑战性的6D物体姿态数据集上的实验表明，本方法在精度与效率上均显著超越现有最优技术。