# Accelerate 3D Object Processing via Spectral Layout

arXiv: https://arxiv.org/abs/2110.12621 · HTML: https://mlsanity.com/paper/2110.12621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks](https://mlsanity.com/paper/1609.06666/) (2016)
- [Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects](https://mlsanity.com/paper/1911.06283/) (2019)
- [FusionNet: 3D Object Classification Using Multiple Data Representations](https://mlsanity.com/paper/1607.05695/) (2016)
- [A survey of Object Classification and Detection based on 2D/3D data](https://mlsanity.com/paper/1905.12683/) (2019)
- [Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method](https://mlsanity.com/paper/1811.07555/) (2018)

## Abstract (arXiv)

3D image processing is an important problem in computer vision and pattern recognition fields. Compared with 2D image processing, its computation difficulty and cost are much higher due to the extra dimension. To fundamentally address this problem, we propose to embed the essential information in a 3D object into 2D space via spectral layout. Specifically, we construct a 3D adjacency graph to capture spatial structure of the 3D voxel grid. Then we calculate the eigenvectors corresponding to the second and third smallest eigenvalues of its graph Laplacian and perform spectral layout to map each voxel into a pixel in 2D Cartesian coordinate plane. The proposed method can achieve high quality 2D representations for 3D objects, which enables to use 2D-based methods to process 3D objects. The experimental results demonstrate the effectiveness and efficiency of our method.