PIZZA：一种强大的仅图像Zero-Shot零CAD方法，用于6 DoF跟踪
PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking
摘要：
在没有先验知识的情况下估计新物体的相对姿态是一个困难的问题，而这是机器人学和增强现实中非常需要的能力。我们提出了一种方法，用于跟踪RGB视频序列中的对象的6D运动时，既没有训练图像，也没有三维几何形状的对象。与以前的工作相比，我们的方法可以立即考虑开放世界中的未知对象，而不需要任何先验信息或特定的训练阶段。我们考虑两种架构，一个基于两个帧，另一个依赖于一个Transformer编码器，它可以利用任意数量的过去的帧。我们训练我们的架构只使用合成渲染域随机化。我们在具有挑战性的数据集上的结果与以前需要更多信息（目标对象的训练图像，3D模型和/或深度数据）的工作相当。我们的源代码可以在https://github.com/nv-nguyen/pizza上找到
英文摘要：
Estimating the relative pose of a new object without prior knowledge is a hard problem, while it is an ability very much needed in robotics and Augmented Reality. We present a method for tracking the 6D motion of objects in RGB video sequences when neither the training images nor the 3D geometry of the objects are available. In contrast to previous works, our method can therefore consider unknown objects in open world instantly, without requiring any prior information or a specific training phase. We consider two architectures, one based on two frames, and the other relying on a Transformer Encoder, which can exploit an arbitrary number of past frames. We train our architectures using only synthetic renderings with domain randomization. Our results on challenging datasets are on par with previous works that require much more information (training images of the target objects, 3D models, and/or depth data). Our source code is available at https://github.com/nv-nguyen/pizza
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
