SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection

@article{Yavartanoo2018SPNetD3,
  title={SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection},
  author={Mohsen Yavartanoo and Euyoung Kim and Kyoung Mu Lee},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.01571}
}
We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. [...] Key Method We then present a shallow 2D convolutional neural network (CNN) to estimate the object category followed by view ensemble, which combines the responses from multiple views of the object to further enhance the predictions.Expand
31 Citations
Aggregated Deep Convolutional Neural Networks for Multi-View 3D Object Retrieval
Joint Multi-view 2D Convolutional Neural Networks for 3D Object Classification
  • PDF
MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks
  • 4
  • PDF
A Hybrid Two-Stage 3D Object Recognition from Orthogonal Projections
Triplanar convolution with shared 2D kernels for 3D classification and shape retrieval
  • 2
  • PDF
DRCNN: Dynamic Routing Convolutional Neural Network for Multi-View 3D Object Recognition
  • 1
Equivariant Multi-View Networks
  • 24
  • PDF
Hierarchical Graph Attention Based Multi-View Convolutional Neural Network for 3D Object Recognition
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 40 REFERENCES
DeepPano: Deep Panoramic Representation for 3-D Shape Recognition
  • 284
  • Highly Influential
  • PDF
LonchaNet: A sliced-based CNN architecture for real-time 3D object recognition
  • 35
Orientation-boosted Voxel Nets for 3D Object Recognition
  • 150
  • Highly Influential
  • PDF
VoxNet: A 3D Convolutional Neural Network for real-time object recognition
  • Daniel Maturana, S. Scherer
  • Computer Science
  • 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2015
  • 1,572
  • Highly Influential
  • PDF
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • 3,714
  • PDF
OctNet: Learning Deep 3D Representations at High Resolutions
  • 718
  • PDF
Multi-view Convolutional Neural Networks for 3D Shape Recognition
  • 1,504
  • Highly Influential
  • PDF
3D ShapeNets: A deep representation for volumetric shapes
  • 2,195
  • Highly Influential
  • PDF
...
1
2
3
4
...