Projective Feature Learning for 3D Shapes with Multi-View Depth Images

@article{Xie2015ProjectiveFL,
  title={Projective Feature Learning for 3D Shapes with Multi-View Depth Images},
  author={Zhige Xie and Kai Xu and Wen Shan and Ligang Liu and Yueshan Xiong and Hui Huang},
  journal={Comput. Graph. Forum},
  year={2015},
  volume={34},
  pages={1-11}
}
Feature learning for 3D shapes is challenging due to the lack of natural paramterization for 3D surface models. We adopt the multi-view depth image representation and propose Multi-View Deep Extreme Learning Machine (MVD-ELM) to achieve fast and quality projective feature learning for 3D shapes. In contrast to existing multiview learning approaches, our method ensures the feature maps learned for different views are mutually dependent via shared weights and in each layer, their unprojections… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 23 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 35 REFERENCES

An insight into extreme learning machines : Random neurons , random features and kernels

  • Z HU Q.-Y., S IEW C.-K.
  • Cognitive Computation
  • 2014

Similar Papers

Loading similar papers…