Traditional geometric registration based estimation methods only exploit the
CAD model implicitly, which leads to their dependence on observation quality
and deficiency to occlusion.To address the problem,the paper proposes a
bidirectional correspondence prediction network with a point-wise
attention-aware mechanism. This network not only requires the model points to
predict the correspondence but also explicitly models the geometric
similarities between observations and the model prior.} Our key insight is that
the correlations between each model point and scene point provide essential
information for learning point-pair matches. To further tackle the correlation
noises brought by feature distribution divergence, we design a simple but
effective pseudo-siamese network to improve feature homogeneity.Experimental
results on the public datasets of LineMOD, YCB-Video, and Occ-LineMOD show that
the proposed method achieves better performance than other state-of-the-art
methods under the same evaluation criteria. Its robustness in estimating poses
is greatly improved, especially in an environment with severe occlusions.

传统的几何注册方法只隐含地利用了 CAD 模型，这导致它们对观察质量的依赖性和遮挡缺陷。为了解决这个问题，本文提出了一种具有点对注意机制的双向对应预测网络，它不仅需要模型点预测对应关系，还明确地建模了观察和模型先验之间的几何相似性。我们的关键见解是，每个模型点与场景点之间的相关性为学习点对匹配提供了必要的信息。为了进一步解决特征分布差异带来的相关性噪声，我们设计了一个简单而有效的伪孪生网络来提高特征的一致性。在 LineMOD、YCB-Video 和 Occ-LineMOD 的公共数据集上的实验结果表明，所提出的方法在相同评价标准下取得了比其他最先进方法更好的性能。它的姿态估计的稳健性得到了极大的改善，特别是在遭受严重遮挡的环境中。