This paper presents an efficient symmetry-agnostic and correspondence-free framework, referred to as SC6D, for 6D object pose estimation from a single monocular RGB image. SC6D requires neither the 3D CAD model of the object nor any prior knowledge of the symmetries. The pose estimation is decomposed into three sub-tasks: a) object 3D rotation representation learning and matching; b) estimation of the 2D location of the object center; and c) scale-invariant distance estimation (the translation along the z-axis) via classification. SC6D is evaluated on three benchmark datasets, T-LESS, YCB-V, and ITODD, and results in state-of-the-art performance on the T-LESS dataset. Moreover, SC6D is computationally much more efficient than the previous state-of-the-art method SurfEmb. The implementation and pre-trained models are publicly available at https://github.com/dingdingcai/SC6D-pose.
翻译:本文件介绍了一个称为SC6D的高效对称-平衡和无对应框架,用于6D对象根据单单单的 RGB 图像进行估计。 SC6D 既不要求该对象的 3D CAD 模型,也不要求事先知道对称性。 构成的估算被分解成三个子任务:(a) 对象 3D 旋转代表制学习和匹配;(b) 估计物体中心2D 的位置;以及(c) 通过分类进行比例变化中距离估计(沿 z- 轴进行翻译)。 SC6D 评估了三个基准数据集,即 T- LESS、 YCB-V 和 ITODD, 以及T- LES 数据集的最新性能结果。此外, SC6D 与先前的状态-艺术方法SurfEmb相比,计算效率要高得多。 实施和预先培训模型可在https://github.com/dingdingcai/SC6Dposi 上公开查阅。