# SnapshotNet: Self-supervised Feature Learning for Point Cloud Data Segmentation Using Minimal Labeled Data

arXiv: https://arxiv.org/abs/2201.04833 · HTML: https://mlsanity.com/paper/2201.04833/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 19 of 19)

- [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)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark](https://mlsanity.com/paper/1704.03847/) (2017)
- [Deep Projective 3D Semantic Segmentation](https://mlsanity.com/paper/1705.03428/) (2017)
- [Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction](https://mlsanity.com/paper/1811.11387/) (2018)
- [3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation](https://mlsanity.com/paper/2002.10893/) (2020)
- [Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels](https://mlsanity.com/paper/2004.04091/) (2020)
- [Fully-Convolutional Point Networks for Large-Scale Point Clouds](https://mlsanity.com/paper/1808.06840/) (2018)
- [Unsupervised Learning of Intrinsic Structural Representation Points](https://mlsanity.com/paper/2003.01661/) (2020)
- [Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation](https://mlsanity.com/paper/1908.08854/) (2019)
- [Self-Supervised Deep Learning on Point Clouds by Reconstructing Space](https://mlsanity.com/paper/1901.08396/) (2019)

## Built on by (most cited first, 3 of 3)

- [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2207.09084/) (2022)
- [ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification](https://mlsanity.com/paper/2401.08210/) (2024)
- [Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution](https://mlsanity.com/paper/2207.01181/) (2022)

## Abstract (arXiv)

Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works on the unlabeled point cloud data of a complex 3D scene. The SnapshotNet pipeline includes three stages. In the snapshot capturing stage, snapshots, which are defined as local collections of points, are sampled from the point cloud scene. A snapshot could be a view of a local 3D scan directly captured from the real scene, or a virtual view of such from a large 3D point cloud dataset. Snapshots could also be sampled at different sampling rates or fields of view (FOVs), thus multi-FOV snapshots, to capture scale information from the scene. In the feature learning stage, a new pre-text task called multi-FOV contrasting is proposed to recognize whether two snapshots are from the same object or not, within the same FOV or across different FOVs. Snapshots go through two self-supervised learning steps: the contrastive learning step with both part and scale contrasting, followed by a snapshot clustering step to extract higher level semantic features. Then a weakly-supervised segmentation stage is implemented by first training a standard SVM classifier on the learned features with a small fraction of labeled snapshots. The trained SVM is used to predict labels for input snapshots and predicted labels are converted into point-wise label assignments for semantic segmentation of the entire scene using a voting procedure. The experiments are conducted on the Semantic3D dataset and the results have shown that the proposed method is capable of learning effective features from snapshots of complex scene data without any labels. Moreover, the proposed method has shown advantages when comparing to the SOA method on weakly-supervised point cloud semantic segmentation.