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

arXiv: https://arxiv.org/abs/1811.01571 · HTML: https://mlsanity.com/paper/1811.01571/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation](https://mlsanity.com/paper/2110.07882/) (2021)
- [SL3D: Self-supervised-Self-labeled 3D Recognition](https://mlsanity.com/paper/2210.16810/) (2022)
- [Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification](https://mlsanity.com/paper/2306.05553/) (2023)
- [Circular-Symmetric Correlation Layer based on FFT](https://mlsanity.com/paper/2107.12480/) (2021)
- [MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation](https://mlsanity.com/paper/2105.13277/) (2021)
- [Improvising the Learning of Neural Networks on Hyperspherical Manifold](https://mlsanity.com/paper/2109.14746/) (2021)
- [Gaussian map predictions for 3D surface feature localisation and counting](https://mlsanity.com/paper/2112.03736/) (2021)
- [Face recognition on point cloud with cgan-top for denoising](https://mlsanity.com/paper/2506.06864/) (2025)

## Abstract (arXiv)

We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. 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. Specifically, the proposed approach consists of four stages: (1) Stereographic projection of a 3D object, (2) view-specific feature learning, (3) view selection and (4) view ensemble. The proposed approach performs comparably to the state-of-the-art methods while having substantially lower GPU memory as well as network parameters. Despite its lightness, the experiments on 3D object classification and shape retrievals demonstrate the high performance of the proposed method.