VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification

no code implementations • 20 Aug 2018 • Songle Chen, Lintao Zheng, Yan Zhang, Zhixin Sun, Kai Xu

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification.

3D Shape Classification Classification +2

3D Shape Segmentation via Shape Fully Convolutional Networks

no code implementations • 28 Feb 2017 • Pengyu Wang, Yuan Gan, Panpan Shui, Fenggen Yu, Yan Zhang, Songle Chen, Zhengxing Sun

3D shapes are represented as graph structures in the SFCN architecture, based on novel graph convolution and pooling operations, which are similar to convolution and pooling operations used on images.

Image Segmentation Segmentation +1