# Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors

arXiv: https://arxiv.org/abs/2209.12770 · HTML: https://mlsanity.com/paper/2209.12770/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 61 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://mlsanity.com/paper/1704.02901/) (2017)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network](https://mlsanity.com/paper/1811.02565/) (2018)
- [3D Shape Segmentation with Projective Convolutional Networks](https://mlsanity.com/paper/1612.02808/) (2016)
- [Adaptive Graph Convolution for Point Cloud Analysis](https://mlsanity.com/paper/2108.08035/) (2021)
- [GIFT: A Real-time and Scalable 3D Shape Search Engine](https://mlsanity.com/paper/1604.01879/) (2016)
- [Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features](https://mlsanity.com/paper/1904.10014/) (2019)
- [Point Attention Network for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1909.12663/) (2019)
- [Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition](https://mlsanity.com/paper/1906.01592/) (2019)
- [Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling](https://mlsanity.com/paper/1912.10775/) (2019)
- [Momen(e)t: Flavor the Moments in Learning to Classify Shapes](https://mlsanity.com/paper/1812.07431/) (2018)
- [GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud](https://mlsanity.com/paper/1905.08705/) (2019)
- [Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms](https://mlsanity.com/paper/2109.02711/) (2021)
- [3D Object Classification via Spherical Projections](https://mlsanity.com/paper/1712.04426/) (2017)
- [3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks](https://mlsanity.com/paper/1711.08241/) (2017)
- [3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds](https://mlsanity.com/paper/1811.02191/) (2018)
- [Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables](https://mlsanity.com/paper/1908.08996/) (2019)
- [Multi-level 3D CNN for Learning Multi-scale Spatial Features](https://mlsanity.com/paper/1805.12254/) (2018)

## Abstract (arXiv)

3D point clouds have attracted increasing attention in architecture, engineering, and construction due to their high-quality object representation and efficient acquisition methods. Consequently, many point cloud feature detection methods have been proposed in the literature to automate some workflows, such as their classification or part segmentation. Nevertheless, the performance of point cloud automated systems significantly lags behind their image counterparts. While part of this failure stems from the irregularity, unstructuredness, and disorder of point clouds, which makes the task of point cloud feature detection significantly more challenging than the image one, we argue that a lack of inspiration from the image domain might be the primary cause of such a gap. Indeed, given the overwhelming success of Convolutional Neural Networks (CNNs) in image feature detection, it seems reasonable to design their point cloud counterparts, but none of the proposed approaches closely resembles them. Specifically, even though many approaches generalise the convolution operation in point clouds, they fail to emulate the CNNs multiple-feature detection and pooling operations. For this reason, we propose a graph convolution-based unit, dubbed Shrinking unit, that can be stacked vertically and horizontally for the design of CNN-like 3D point cloud feature extractors. Given that self, local and global correlations between points in a point cloud convey crucial spatial geometric information, we also leverage them during the feature extraction process. We evaluate our proposal by designing a feature extractor model for the ModelNet-10 benchmark dataset and achieve 90.64% classification accuracy, demonstrating that our innovative idea is effective. Our code is available at github.com/albertotamajo/Shrinking-unit.