6D pose estimation from a single RGB image is a fundamental task in computer vision. The current top-performing deep learning-based methods rely on an indirect strategy, i.e., first establishing 2D-3D correspondences between the coordinates in the image plane and object coordinate system, and then applying a variant of the P$n$P/RANSAC algorithm. However, this two-stage pipeline is not end-to-end trainable, thus is hard to be employed for many tasks requiring differentiable poses. On the other hand, methods based on direct regression are currently inferior to geometry-based methods. In this work, we perform an in-depth investigation on both direct and indirect methods, and propose a simple yet effective Geometry-guided Direct Regression Network (GDR-Net) to learn the 6D pose in an end-to-end manner from dense correspondence-based intermediate geometric representations. Extensive experiments show that our approach remarkably outperforms state-of-the-art methods on LM, LM-O and YCB-V datasets. The code will be available at https://git.io/GDR-Net.

中文翻译：

---

GDR-Net：用于单眼6D对象姿态估计的几何引导直接回归网络

从单个RGB图像进行6D姿态估计是计算机视觉中的基本任务。当前基于表现最佳的深度学习方法依赖于间接策略，即首先在图像平面中的坐标与对象坐标系之间建立2D-3D对应关系，然后应用P $ n $ P / RANSAC的变体算法。但是，这种两阶段流水线不是端到端可训练的，因此很难用于许多需要可区分姿势的任务。另一方面，基于直接回归的方法目前不如基于几何的方法。在这项工作中，我们对直接和间接方法进行了深入的研究，并提出一种简单而有效的几何引导直接回归网络（GDR-Net），以从密集的基于对应的中间几何表示形式以端到端的方式学习6D姿态。大量的实验表明，在LM，LM-O和YCB-V数据集上，我们的方法明显优于最新方法。该代码将在https://git.io/GDR-Net上提供。