# Self-Supervised Deep Learning on Point Clouds by Reconstructing Space

arXiv: https://arxiv.org/abs/1901.08396 · HTML: https://mlsanity.com/paper/1901.08396/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

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

- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud](https://mlsanity.com/paper/2404.16432/) (2024)
- [SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data](https://mlsanity.com/paper/2201.04833/) (2022)
- [A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2505.24641/) (2025)
- [Weakly-Supervised Semantic Segmentation of Ships Using Thermal Imagery](https://mlsanity.com/paper/2212.13170/) (2022)
- [Self-Supervised Learning for Point Clouds Data: A Survey](https://mlsanity.com/paper/2305.11881/) (2023)

## Abstract (arXiv)

Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised learning tasks such as object classification and semantic segmentation. While massive point cloud datasets can be captured using modern scanning technology, manually labelling such large 3D point clouds for supervised learning tasks is a cumbersome process. This necessitates methods that can learn from unlabelled data to significantly reduce the number of annotated samples needed in supervised learning. We propose a self-supervised learning task for deep learning on raw point cloud data in which a neural network is trained to reconstruct point clouds whose parts have been randomly rearranged. While solving this task, representations that capture semantic properties of the point cloud are learned. Our method is agnostic of network architecture and outperforms current unsupervised learning approaches in downstream object classification tasks. We show experimentally, that pre-training with our method before supervised training improves the performance of state-of-the-art models and significantly improves sample efficiency.