3D convolutional neural networks by modal fusion
| Autor: | Leonidas J. Guibas, Soeren Pirk, Eiichi Yoshida, Yusuke Yoshiyasu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Surface (mathematics)
business.industry Computer science 020207 software engineering Pattern recognition 02 engineering and technology 010501 environmental sciences Object (computer science) 01 natural sciences Convolutional neural network Modal 0202 electrical engineering electronic engineering information engineering Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | ICIP |
| DOI: | 10.1109/icip.2017.8296587 |
| Popis: | We propose multi-view and volumetric convolutional neural networks (ConvNets) for 3D shape recognition, which combines surface normal and height fields to capture local geometry and physical size of an object. This strategy helps distinguishing between objects with similar geometries but different sizes. This is especially useful for enhancing volumetric ConvNets and classifying 3D scans with insufficient surface details. Experimental results on CAD and real-world scan datasets showed that our technique outperforms previous approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|