Existing Object Pose Estimation (OPE) methods for stacked scenarios are not
robust to changes in object scale. This paper proposes a new 6DoF OPE network
(NormNet) for different scale objects in stacked scenarios. Specifically, each
object's scale is first learned with point-wise regression. Then, all objects
in the stacked scenario are normalized into the same scale through semantic
segmentation and affine transformation. Finally, they are fed into a shared
pose estimator to recover their 6D poses. In addition, we introduce a new
Sim-to-Real transfer pipeline, combining style transfer and domain
randomization. This improves the NormNet's performance on real data even if we
only train it on synthetic data. Extensive experiments demonstrate that the
proposed method achieves state-of-the-art performance on public benchmarks and
the MultiScale dataset we constructed. The real-world experiments show that our
method can robustly estimate the 6D pose of objects at different scales.

基于规模不同的堆叠情景中的对象姿态估计，本文提出了一种新的 6DoF OPE 网络 (NormNet)。该网络利用点对点回归学习每个对象的规模，并通过语义分割和仿射变换将堆叠情景中的所有对象归一化到相同的尺度，并通过共享位姿估计器恢复它们的 6D 姿态。此外，我们引入了一种新的 Sim-to-Real 转换流程，结合样式转换和域随机化，提高了 NormNet 在真实数据上的性能，即使只使用合成数据进行训练。大量实验证明了该方法在公共基准和我们构建的 MultiScale 数据集上达到了最先进的性能。真实世界的实验证明了我们的方法能够稳健地估计处于不同尺度的对象的 6D 姿态。