Unsupervised 3D Primitive Shape Detection using Mathematical Models
| Autor: | Guiju Ping, Mahdi Abolfazli Esfahani, Han Wang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Training set
Mathematical model business.industry Computer science Deep learning Data_MISCELLANEOUS 05 social sciences Point cloud 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Annotation 0502 economics and business Task analysis Artificial intelligence 050207 economics business computer 0105 earth and related environmental sciences |
| Zdroj: | ICARCV |
| DOI: | 10.1109/icarcv50220.2020.9305494 |
| Popis: | This study aims to propose the first unsupervised deep learning based framework to detect primitive shapes in unorganized point clouds. The benefits of the proposed model are as follows: first, modeling primitive shapes mathematically and making the annotation and generation of training data automatically can assist in training a network in an unsupervised manner without using any pre-annotated datasets. The proposed approach is able to expand to other 3D point clouds related tasks when the datasets are not big enough. Experiments and results demonstrate that the proposed unsupervised methods can achieve an accuracy on par with supervised approach for primitive shape detection in 3d point clouds. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|