We propose a single-shot approach to determining 6-DoF pose of an object with
available 3D computer-aided design (CAD) model from a single RGB image. Our
method, dubbed MRC-Net, comprises two stages. The first performs pose
classification and renders the 3D object in the classified pose. The second
stage performs regression to predict fine-grained residual pose within class.
Connecting the two stages is a novel multi-scale residual correlation (MRC)
layer that captures high-and-low level correspondences between the input image
and rendering from first stage. MRC-Net employs a Siamese network with shared
weights between both stages to learn embeddings for input and rendered images.
To mitigate ambiguity when predicting discrete pose class labels on symmetric
objects, we use soft probabilistic labels to define pose class in the first
stage. We demonstrate state-of-the-art accuracy, outperforming all competing
RGB-based methods on four challenging BOP benchmark datasets: T-LESS, LM-O,
YCB-V, and ITODD. Our method is non-iterative and requires no complex
post-processing.

我们提出了一种单次拍摄方法，可以从一张 RGB 图像中确定具有 3D CAD 模型的物体的 6 自由度姿态。我们的方法称为 MRC-Net，包括两个阶段，利用 MRC 层获得输入图像和第一阶段渲染的高低级对应关系。MRC-Net 采用具有共享权重的孪生网络学习输入和渲染图像的嵌入表示。我们的方法在四个具有挑战性的 BOP 基准数据集上表现出色，超过了所有竞争的基于 RGB 的方法。我们的方法非迭代且不需要复杂的后处理。