论文标题
单拍6D对象姿势估计
Single Shot 6D Object Pose Estimation
论文作者
论文摘要
在本文中，我们介绍了一种基于深度图像的刚性对象的6D对象的新颖单拍方法。为此，采用了一个完全卷积的神经网络，其中3D输入数据被空间离散，并且姿势估计被视为在当地在所得量元素上本地解决的回归任务。对于GPU上的65 fps，我们的对象姿势网络（OP-NET）非常快，对端到端进行了优化，并同时估计图像中多个对象的6D姿势。我们的方法不需要手动的6D姿势被宣布的现实世界数据集并转移到现实世界，尽管完全接受了合成数据的培训。提出的方法在公共基准数据集上进行了评估，在该数据集中，我们可以证明最先进的方法的表现明显胜过。
In this paper, we introduce a novel single shot approach for 6D object pose estimation of rigid objects based on depth images. For this purpose, a fully convolutional neural network is employed, where the 3D input data is spatially discretized and pose estimation is considered as a regression task that is solved locally on the resulting volume elements. With 65 fps on a GPU, our Object Pose Network (OP-Net) is extremely fast, is optimized end-to-end, and estimates the 6D pose of multiple objects in the image simultaneously. Our approach does not require manually 6D pose-annotated real-world datasets and transfers to the real world, although being entirely trained on synthetic data. The proposed method is evaluated on public benchmark datasets, where we can demonstrate that state-of-the-art methods are significantly outperformed.
