# Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model

arXiv: https://arxiv.org/abs/2202.06407 · HTML: https://mlsanity.com/paper/2202.06407/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 13 Feb 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [Point Convolutional Neural Networks by Extension Operators](https://mlsanity.com/paper/1803.10091/) (2018)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models](https://mlsanity.com/paper/1704.01222/) (2017)
- [DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing](https://mlsanity.com/paper/1909.03669/) (2019)
- [Multiresolution Tree Networks for 3D Point Cloud Processing](https://mlsanity.com/paper/1807.03520/) (2018)
- [Point Cloud GAN](https://mlsanity.com/paper/1810.05795/) (2018)
- [RGCNN: Regularized Graph CNN for Point Cloud Segmentation](https://mlsanity.com/paper/1806.02952/) (2018)
- [VConv-DAE: Deep Volumetric Shape Learning Without Object Labels](https://mlsanity.com/paper/1604.03755/) (2016)
- [Point Attention Network for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1909.12663/) (2019)
- [Spectral-GANs for High-Resolution 3D Point-cloud Generation](https://mlsanity.com/paper/1912.01800/) (2019)
- [Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations](https://mlsanity.com/paper/1911.05277/) (2019)

## Built on by (most cited first, 1 of 1)

- [T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition](https://mlsanity.com/paper/2402.19264/) (2024)

## Abstract (arXiv)

In this paper we present SA-CNN, a hierarchical and lightweight self-attention based encoding and decoding architecture for representation learning of point cloud data. The proposed SA-CNN introduces convolution and transposed convolution stacks to capture and generate contextual information among unordered 3D points. Following conventional hierarchical pipeline, the encoding process extracts feature in local-to-global manner, while the decoding process generates feature and point cloud in coarse-to-fine, multi-resolution stages. We demonstrate that SA-CNN is capable of a wide range of applications, namely classification, part segmentation, reconstruction, shape retrieval, and unsupervised classification. While achieving the state-of-the-art or comparable performance in the benchmarks, SA-CNN maintains its model complexity several order of magnitude lower than the others. In term of qualitative results, we visualize the multi-stage point cloud reconstructions and latent walks on rigid objects as well as deformable non-rigid human and robot models.