“6D Pose Estimation with Two-stream Net” by Yang and Jia

  • ©Xiaolong Yang and Xiaohong Jia

  • ©Xiaolong Yang and Xiaohong Jia

  • ©Xiaolong Yang and Xiaohong Jia



Entry Number: 40


    6D Pose Estimation with Two-stream Net



    In this poster, we present a heterogeneous architecture for estimating 6D object pose from RGB images. First, we use a two-stream network to extract robust 3D-to-2D embedding feature correspondence. The segmentation stream processes the RGB information and spatial features individually. Then, we construct another fusion network to couple color and positional features, and predict the locations of keypoints in the regression stream. The pose can be obtained by an efficient RANSAC-based PnP algorithm. Moreover, we design an end-to-end iterative pose refinement procedure that further improves the reliable pose estimation. Our method outperforms state-of-the-art approaches in two public datasets.



    This work was funded by the National Natural Science Foundation of China (61872354), Beijing Natural Science Foundation (Z190004), and Alibaba Group through Alibaba Innovative Research Program.


ACM Digital Library Publication:

Overview Page: