Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 22, Issue 12, Pages 2339-2343Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2015.2480802
Keywords
3-D shape; classification; convolutional neural networks; panorama; retrieval
Categories
Funding
- National Natural Science Foundation of China (NSFC) [61222308, 61573160]
- Excellent Talents in University [NCET-12-0217]
Ask authors/readers for more resources
This letter introduces a robust representation of 3-D shapes, named DeepPano, learned with deep convolutional neural networks (CNN). Firstly, each 3-D shape is converted into a panoramic view, namely a cylinder projection around its principle axis. Then, a variant of CNN is specifically designed for learning the deep representations directly from such views. Different from typical CNN, a row-wise max-pooling layer is inserted between the convolution and fully-connected layers, making the learned representations invariant to the rotation around a principle axis. Our approach achieves state-of-the-art retrieval/classification results on two large-scale 3-D model datasets (ModelNet-10 and ModelNet-40), outperforming typical methods by a large margin.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available