RoboTAG：基于拓扑对齐图的端到端机器人位姿估计
RoboTAG: End-to-end Robot Pose Estimation via Topological Alignment Graph
把机器人位姿估计建模成 2D/3D 双分支的拓扑对齐图，用闭环上的跨分支一致性监督替代大量标注，这个「图节点=相机/机器人状态、边=对齐关系」的构造方式可直接迁移到单目相机重定位、手眼标定和 sim-to-real 位姿回归任务中。
原文依据 we propose Robot Topological Alignment Graph (RoboTAG), which incorporates a 3D branch to inject 3D priors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单目 RGB 图像估计机器人位姿是机器人与计算机视觉领域的一项挑战。现有方法通常在 2D 视觉骨干网络之上构建网络，并严重依赖标注数据进行训练，而真实场景中标注往往稀缺，从而造成仿真到现实的差距。此外，这些方法将基于 3D 的问题退化为 2D 域，忽略了 3D 先验。为解决上述问题，我们提出机器人拓扑对齐图（RoboTAG），它引入一个 3D 分支以注入 3D 先验，同时使 2D 与 3D 表征协同演化，从而缓解对标签的依赖。具体而言，RoboTAG 由一个 3D 分支和一个 2D 分支构成，其中节点表示相机与机器人系统的状态，边刻画这些变量之间的依赖关系或表示它们之间的对齐。随后在图中定义闭环，并在闭环上施加跨分支的一致性监督。实验结果表明，我们的方法在不同机器人类型上均有效，这为缓解机器人领域的数据瓶颈提供了新的可能。
英文原文摘要 1105 字符
Estimating robot pose from a monocular RGB image is a challenge in robotics and computer vision. Existing methods typically build networks on top of 2D visual backbones and depend heavily on labeled data for training, which is often scarce in real-world scenarios, causing a sim-to-real gap. Moreover, these approaches reduce the 3D-based problem to 2D domain, neglecting the 3D priors. To address these, we propose Robot Topological Alignment Graph (RoboTAG), which incorporates a 3D branch to inject 3D priors while enabling co-evolution of the 2D and 3D representations, alleviating the reliance on labels. Specifically, the RoboTAG consists of a 3D branch and a 2D branch, where nodes represent the states of the camera and robot system, and edges capture the dependencies between these variables or denote alignments between them. Closed loops are then defined in the graph, on which a consistency supervision across branches can be applied. Experimental results demonstrate that our method is effective across robot types, suggesting new possibilities of alleviating the data bottleneck in robotics.