# Attention Models for Point Clouds in Deep Learning: A Survey

arXiv: https://arxiv.org/abs/2102.10788 · HTML: https://mlsanity.com/paper/2102.10788/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 83 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 30 of 40)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://mlsanity.com/paper/1907.10844/) (2019)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [An Attentive Survey of Attention Models](https://mlsanity.com/paper/1904.02874/) (2019)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)
- [Point Cloud Completion by Skip-attention Network with Hierarchical Folding](https://mlsanity.com/paper/2005.03871/) (2020)
- [DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing](https://mlsanity.com/paper/1909.03669/) (2019)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [Attention in Natural Language Processing](https://mlsanity.com/paper/1902.02181/) (2019)
- [MLCVNet: Multi-Level Context VoteNet for 3D Object Detection](https://mlsanity.com/paper/2004.05679/) (2020)
- [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016)
- [DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration](https://mlsanity.com/paper/1905.04153/) (2019)
- [Detail Preserved Point Cloud Completion via Separated Feature Aggregation](https://mlsanity.com/paper/2007.02374/) (2020)
- [PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval](https://mlsanity.com/paper/1904.09793/) (2019)
- [SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition](https://mlsanity.com/paper/2011.12430/) (2020)
- [DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization](https://mlsanity.com/paper/2007.09217/) (2020)
- [PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds](https://mlsanity.com/paper/1911.12408/) (2019)
- [PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition](https://mlsanity.com/paper/1808.07659/) (2018)
- [Hierarchical Attention Learning of Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/2010.05762/) (2020)
- [PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization](https://mlsanity.com/paper/2012.00972/) (2020)
- [L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention](https://mlsanity.com/paper/1908.00720/) (2019)
- [SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization](https://mlsanity.com/paper/2012.04439/) (2020)
- [PIC-Net: Point Cloud and Image Collaboration Network for Large-Scale Place Recognition](https://mlsanity.com/paper/2008.00658/) (2020)

## Built on by (most cited first, 6 of 6)

- [LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling](https://mlsanity.com/paper/2202.06263/) (2022)
- [3D Multiple Object Tracking on Autonomous Driving: A Literature Review](https://mlsanity.com/paper/2309.15411/) (2023)
- [Graph Structure from Point Clouds: Geometric Attention is All You Need](https://mlsanity.com/paper/2307.16662/) (2023)
- [Curvature Informed Furthest Point Sampling](https://mlsanity.com/paper/2411.16995/) (2024)
- [Using Gradient to Boost the Generalization Performance of Deep Learning Models for Fluid Dynamics](https://mlsanity.com/paper/2212.00716/) (2022)
- [AGAR: Attention Graph-RNN for Adaptative Motion Prediction of Point Clouds of Deformable Objects](https://mlsanity.com/paper/2307.09936/) (2023)

## Abstract (arXiv)

Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks. However, creating feature representation of robust, discriminative from unordered and irregular point clouds is challenging. In this paper, our ultimate goal is to provide a comprehensive overview of the point clouds feature representation which uses attention models. More than 75+ key contributions in the recent three years are summarized in this survey, including the 3D objective detection, 3D semantic segmentation, 3D pose estimation, point clouds completion etc. We provide a detailed characterization (1) the role of attention mechanisms, (2) the usability of attention models into different tasks, (3) the development trend of key technology.