论文标题
COSYPOSE：一致的多视图多对象6D姿势估计
CosyPose: Consistent multi-view multi-object 6D pose estimation
论文作者
论文摘要
我们介绍了一种方法，用于在一组未知相机视点的输入图像捕获的场景中恢复多个已知对象的6D姿势。首先，我们提出一个单视图单对象6D姿势估计方法，我们用来生成6D对象姿势假设。其次，我们开发了一种可靠的方法，用于匹配单个6D对象在不同输入映像上构成假设，以便在单个一致的场景中共同估算所有对象的摄像头观点和6D姿势。我们的方法明确处理对象对称性，不需要深度测量，对于丢失或错误的对象假设是可靠的，并且会自动恢复场景中对象的数量。第三，我们开发了一种给定多个对象假设及其跨视图的对应的全局场景细化方法。这是通过解决对象级束调整问题来完善相机和对象的姿势以最大程度地减少所有视图中的再投影错误的姿势来实现的。我们证明，所提出的方法称为COSYPOSE，优于单视图和多视图6D对象姿势效率估计的当前最新结果，这是在两个具有挑战性的基准上的巨大余量：YCB-VIDEO和T-less Datasets。代码和预训练的模型可在项目网页https://www.di.ens.fr/willow/research/cosypose/上找到。
We introduce an approach for recovering the 6D pose of multiple known objects in a scene captured by a set of input images with unknown camera viewpoints. First, we present a single-view single-object 6D pose estimation method, which we use to generate 6D object pose hypotheses. Second, we develop a robust method for matching individual 6D object pose hypotheses across different input images in order to jointly estimate camera viewpoints and 6D poses of all objects in a single consistent scene. Our approach explicitly handles object symmetries, does not require depth measurements, is robust to missing or incorrect object hypotheses, and automatically recovers the number of objects in the scene. Third, we develop a method for global scene refinement given multiple object hypotheses and their correspondences across views. This is achieved by solving an object-level bundle adjustment problem that refines the poses of cameras and objects to minimize the reprojection error in all views. We demonstrate that the proposed method, dubbed CosyPose, outperforms current state-of-the-art results for single-view and multi-view 6D object pose estimation by a large margin on two challenging benchmarks: the YCB-Video and T-LESS datasets. Code and pre-trained models are available on the project webpage https://www.di.ens.fr/willow/research/cosypose/.
