We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenarios. Our approach can efficiently detect the traffic participants from a monocular RGB image while simultaneously regressing their 3D translation and rotation vectors. The proposed method 6D-VNet, extends the Mask R-CNN by adding customised heads for predicting vehicle’s finer class, rotation and translation. It is trained end-to-end compared to previous methods. Furthermore, we show that the inclusion of translational regression in the joint losses is crucial for the 6DoF pose estimation task, where object translation distance along longitudinal axis varies significantly, e.g., in autonomous driving scenarios. Additionally, we incorporate the mutual information between traffic participants via a modified non-local block to capture the spatial dependencies among the detected objects. As opposed to the original non-local block implementation, the proposed weighting modification takes the spatial neighbouring information into consideration whilst counteracting the effect of extreme gradient values. We evaluate our method on the challenging real-world Pascal3D+ dataset and our 6D-VNet reaches the 1st place in ApolloScape challenge 3D Car Instance task (Apolloscape, 2018), (Huang et al. , 2018).

中文翻译：

---

从单眼RGB图像进行端到端6DoF姿势估计

我们为6DoF对象姿态估计提供了一个概念上简单的框架，尤其是在自动驾驶场景中。我们的方法可以有效地从单眼RGB图像中检测交通参与者，同时对他们的3D平移和旋转矢量进行回归。所提出的方法6D-VNet通过添加定制的喷头来扩展Mask R-CNN，以预测车辆的更精细的分类，旋转和平移。与以前的方法相比，它是经过端到端训练的。此外，我们表明，在关节损失中包括平移回归对于6DoF姿态估计任务至关重要，在6DoF姿态估计任务中，沿纵轴的对象平移距离会发生很大变化，例如在自动驾驶场景中。此外，我们通过修改后的非本地块合并交通参与者之间的相互信息，以捕获检测到的对象之间的空间依赖性。与原始的非局部块实现相反，所提出的加权修改在抵消极端梯度值的影响的同时考虑了空间邻近信息。我们在具有挑战性的真实世界Pascal3D +数据集上评估了我们的方法，我们的6D-VNet在ApolloScape挑战3D汽车实例任务（Apolloscape，2018）中排名第一等。 ，2018）。