# 3D Object Classification via Spherical Projections

arXiv: https://arxiv.org/abs/1712.04426 · HTML: https://mlsanity.com/paper/1712.04426/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2017.

## Built on by (most cited first, 9 of 9)

- [ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators](https://mlsanity.com/paper/2108.09432/) (2021)
- [SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators](https://mlsanity.com/paper/2201.00112/) (2022)
- [MetaSets: Meta-Learning on Point Sets for Generalizable Representations](https://mlsanity.com/paper/2204.07311/) (2022)
- [Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis](https://mlsanity.com/paper/2212.08892/) (2022)
- [Theoretical bounds on data requirements for the ray-based classification](https://mlsanity.com/paper/2103.09577/) (2021)
- [UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps](https://mlsanity.com/paper/2105.02961/) (2021)
- [ActivationNet: Representation learning to predict contact quality of interacting 3-D surfaces in engineering designs](https://mlsanity.com/paper/2103.11288/) (2021)
- [Gaussian map predictions for 3D surface feature localisation and counting](https://mlsanity.com/paper/2112.03736/) (2021)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)

## Abstract (arXiv)

In this paper, we introduce a new method for classifying 3D objects. Our main idea is to project a 3D object onto a spherical domain centered around its barycenter and develop neural network to classify the spherical projection. We introduce two complementary projections. The first captures depth variations of a 3D object, and the second captures contour-information viewed from different angles. Spherical projections combine key advantages of two main-stream 3D classification methods: image-based and 3D-based. Specifically, spherical projections are locally planar, allowing us to use massive image datasets (e.g, ImageNet) for pre-training. Also spherical projections are similar to voxel-based methods, as they encode complete information of a 3D object in a single neural network capturing dependencies across different views. Our novel network design can fully utilize these advantages. Experimental results on ModelNet40 and ShapeNetCore show that our method is superior to prior methods.