UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation

Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon, Kuk-Jin Yoon

The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2022)

상세내용

BibTeX

저자 : Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon, Kuk-Jin Yoon
논문명 : UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
학회명 : The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2022)
발간년도 : 2022
발간년도 : 2022
발간월 : June
초록 : Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real world. To tackle this problem, we propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called UDA-COPE. Inspired by recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain pose labels. We also introduce a bidirectional filtering method between the predicted normalized object coordinate space (NOCS) map and observed point cloud, to not only make our teacher network more robust to the target domain but also to provide more reliable pseudo labels for the student network training. Extensive experimental results demonstrate the effectiveness of our proposed method both quantitatively and qualitatively. Notably, without leveraging target-domain GT labels, our proposed method achieved comparable or sometimes superior performance to existing methods that depend on the GT labels.

첨부파일

목록