Weakly Supervised 3D Instance Segmentation without Instance-level Annotations
Published in arXiv (Cornell University) • Aug 3, 2023
Authors:,
Shichao Dong
Guosheng Lin
Abstract
3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data. To alleviate the annotation cost, we propose the first weakly-supervised 3D instance segmentation method that only requires cate...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!