Despite the success in 6D pose estimation in bin-picking scenarios, existing methods still struggle to produce accurate prediction results for symmetry objects and real world scenarios. The primary bottlenecks include 1) the ambiguity keypoints caused by object symmetries; 2) the domain gap between real and synthetic data. To circumvent these problem, we propose a new 6D pose estimation network with symmetric-aware keypoint prediction and self-training domain adaptation (SD-Net). SD-Net builds on pointwise keypoint regression and deep hough voting to perform reliable detection keypoint under clutter and occlusion. Specifically, at the keypoint prediction stage, we designe a robust 3D keypoints selection strategy considering the symmetry class of objects and equivalent keypoints, which facilitate locating 3D keypoints even in highly occluded scenes. Additionally, we build an effective filtering algorithm on predicted keypoint to dynamically eliminate multiple ambiguity and outlier keypoint candidates. At the domain adaptation stage, we propose the self-training framework using a student-teacher training scheme. To carefully distinguish reliable predictions, we harnesses a tailored heuristics for 3D geometry pseudo labelling based on semi-chamfer distance. On public Sil'eane dataset, SD-Net achieves state-of-the-art results, obtaining an average precision of 96%. Testing learning and generalization abilities on public Parametric datasets, SD-Net is 8% higher than the state-of-the-art method. The code is available at https://github.com/dingthuang/SD-Net.

翻译：尽管6D姿态估计在拣选场景中已取得显著成功，现有方法在处理对称物体和真实场景时仍难以生成精确预测结果。主要瓶颈包括：1）物体对称性导致的关键点歧义；2）真实数据与合成数据之间的域差异。为解决这些问题，我们提出一种结合对称感知关键点预测与自训练域适应的新型6D姿态估计网络（SD-Net）。SD-Net基于逐点关键点回归与深度霍夫投票，在杂乱和遮挡条件下实现可靠的关键点检测。具体而言，在关键点预测阶段，我们设计了一种考虑物体对称类别和等效关键点的鲁棒3D关键点选择策略，即便在高度遮挡场景中也能有效定位3D关键点。此外，我们构建了基于预测关键点的有效滤波算法，以动态消除多重歧义和离群关键点候选。在域适应阶段，我们提出采用师生训练范式的自训练框架。为精确区分可靠预测，我们利用基于半倒角距离的定制化启发式方法进行3D几何伪标签标注。在公开Sil'eane数据集上，SD-Net取得了平均精度96%的先进结果；在公开Parametric数据集上的学习与泛化能力测试中，SD-Net比现有最优方法高8%。代码已开源：https://github.com/dingthuang/SD-Net。