# What Can be Seen is What You Get: Structure Aware Point Cloud Augmentation

arXiv: https://arxiv.org/abs/2206.09664 · HTML: https://mlsanity.com/paper/2206.09664/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 20 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2103.12978/) (2021)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation](https://mlsanity.com/paper/2008.01550/) (2020)
- [Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation](https://mlsanity.com/paper/2103.14962/) (2021)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2012.04934/) (2020)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation](https://mlsanity.com/paper/2002.10893/) (2020)
- [VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion](https://mlsanity.com/paper/2111.14382/) (2021)
- [Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study](https://mlsanity.com/paper/2004.11803/) (2020)
- [Pattern-Aware Data Augmentation for LiDAR 3D Object Detection](https://mlsanity.com/paper/2112.00050/) (2021)
- [OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation](https://mlsanity.com/paper/1812.02611/) (2018)
- [Multimodal 3D Object Detection from Simulated Pretraining](https://mlsanity.com/paper/1905.07754/) (2019)

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

- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection](https://mlsanity.com/paper/2305.12853/) (2023)
- [Text3DAug -- Prompted Instance Augmentation for LiDAR Perception](https://mlsanity.com/paper/2408.14253/) (2024)
- [MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency](https://mlsanity.com/paper/2303.09219/) (2023)
- [Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensors](https://mlsanity.com/paper/2212.09517/) (2022)
- [ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only](https://mlsanity.com/paper/2407.17197/) (2024)

## Abstract (arXiv)

To train a well performing neural network for semantic segmentation, it is crucial to have a large dataset with available ground truth for the network to generalize on unseen data. In this paper we present novel point cloud augmentation methods to artificially diversify a dataset. Our sensor-centric methods keep the data structure consistent with the lidar sensor capabilities. Due to these new methods, we are able to enrich low-value data with high-value instances, as well as create entirely new scenes. We validate our methods on multiple neural networks with the public SemanticKITTI dataset and demonstrate that all networks improve compared to their respective baseline. In addition, we show that our methods enable the use of very small datasets, saving annotation time, training time and the associated costs.