Thông tin tài liệu
Nhan đề : | Semi-supervised 3D shape segmentation with multilevel consistency and part substitution |
Tác giả : | Chun-Yu, Sun Yu-Qi, Yang Hao-Xiang, Guo |
Năm xuất bản : | 2023 |
Nhà xuất bản : | Springer |
Tóm tắt : | The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data. For the unlabeled data, we present a novel multilevel consistency loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point level, part level, and hierarchical level. For the labeled data, we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance training. |
Mô tả: | CC BY |
URI: | https://link.springer.com/article/10.1007/s41095-022-0281-9 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7325 |
Bộ sưu tập | OER - Công nghệ thông tin |
XEM MÔ TẢ
33
XEM TOÀN VĂN
2
Danh sách tệp tin đính kèm: