FPNN: Field Probing Neural Networks for 3D Data

@inproceedings{Li2016FPNNFP,
  title={FPNN: Field Probing Neural Networks for 3D Data},
  author={Yangyan Li and S{\"o}ren Pirk and Hao Su and Charles Ruizhongtai Qi and Leonidas J. Guibas},
  booktitle={NIPS},
  year={2016}
}
Building discriminative representations for 3D data has been an important task in computer graphics and computer vision research. Convolutional Neural Networks (CNNs) have shown to operate on 2D images with great success for a variety of tasks. Lifting convolution operators to 3D (3DCNNs) seems like a plausible and promising next step. Unfortunately, the… CONTINUE READING