In this paper, we propose a novel real-time 6D object pose estimation framework, named G2L-Net. Our network operates on point clouds from RGB-D detection in a divide-and-conquer fashion. Specifically, our network consists of three steps. First, we extract the coarse object point cloud from the RGB-D image by 2D detection. Second, we feed the coarse object point cloud to a translation localization network to perform 3D segmentation and object translation prediction. Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation. In the third step, we define point-wise embedding vector features to capture viewpoint-aware information. To calculate more accurate rotation, we adopt a rotation residual estimator to estimate the residual between initial rotation and ground truth, which can boost initial pose estimation performance. Our proposed G2L-Net is real-time despite the fact multiple steps are stacked via the proposed coarse-to-fine framework. Extensive experiments on two benchmark datasets show that G2L-Net achieves state-of-the-art performance in terms of both accuracy and speed.
|Title of host publication||IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020|
|Number of pages||10|
|Publication status||Published - 2020|
|Event||2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States|
Duration: 14 Jun 2020 → 19 Jun 2020
|Name||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Publisher||IEEE Computer Society|
|Conference||2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020|
|Period||14/06/20 → 19/06/20|
Bibliographical noteFunding Information:
Acknowledgement We acknowledge MoD/Dstl and EP-SRC (EP/N019415/1) for providing the grant to support the UK academics involvement in MURI project.
© 2020 IEEE.
Copyright 2020 Elsevier B.V., All rights reserved.
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition