Abstract | ||
---|---|---|
6D object pose estimation plays an important role in various applications such as robot manipulation and virtual reality. In this paper, we introduce a graph convolution neural network based method to addresses the problem of estimating the 6D pose of objects from a single RGB-D image. The proposed method fuses the appearance feature of the RGB image with the geometry feature of point clouds to predict pixel-level pose and the network also predicts pixel-level confidences to prune outlier predictions. The inner structure information of point cloud is learned by a graph convolution neural network. Specially, we adopt a residual graph convolution module to learn a discriminative feature. Our network enables end-to-end training and fast inference. The extensive experiments verify the method and the model achieves state-of-the-art for the LINEMOD and LINEMOD-OCCLUSION dataset (ADD-S: 88.68 and 65.38 respectively). |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.knosys.2021.106839 | Knowledge-Based Systems |
Keywords | DocType | Volume |
Pose estimation,Image processing,Deep learning | Journal | 218 |
ISSN | Citations | PageRank |
0950-7051 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pengshuai Yin | 1 | 1 | 1.37 |
Jiayong Ye | 2 | 0 | 0.34 |
Guoshen Lin | 3 | 0 | 0.34 |
Wu Qingyao | 4 | 259 | 33.46 |