# Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds

arXiv: https://arxiv.org/abs/2102.04136 · HTML: https://mlsanity.com/paper/2102.04136/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 8 Feb 2021.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Learning a Predictable and Generative Vector Representation for Objects](https://mlsanity.com/paper/1603.08637/) (2016)
- [Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation](https://mlsanity.com/paper/1806.08756/) (2018)
- [InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset](https://mlsanity.com/paper/1809.00716/) (2018)
- [VConv-DAE: Deep Volumetric Shape Learning Without Object Labels](https://mlsanity.com/paper/1604.03755/) (2016)
- [VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation](https://mlsanity.com/paper/1904.08963/) (2019)
- [View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions](https://mlsanity.com/paper/1811.02744/) (2018)
- [Learning Representations and Generative Models for 3D Point Clouds](https://mlsanity.com/paper/1707.02392/) (2017)
- [Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering](https://mlsanity.com/paper/1905.04571/) (2019)
- [SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes](https://mlsanity.com/paper/1709.07158/) (2017)
- [Adversarial Autoencoders for Compact Representations of 3D Point Clouds](https://mlsanity.com/paper/1811.07605/) (2018)
- [NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler](https://mlsanity.com/paper/1901.09394/) (2019)

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

- [Self-Improving Semantic Perception for Indoor Localisation](https://mlsanity.com/paper/2105.01595/) (2021)

## Abstract (arXiv)

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the context of 3D vision. This, despite the fact that the physical 3D spaces have a similar semantic structure to bodies of text: words are surrounded by words that are semantically related, just like objects are surrounded by other objects that are similar in concept and usage. In this work, we exploit this structure in learning semantically meaningful low dimensional vector representations of objects. We learn these vector representations by mining a dataset of scanned 3D spaces using an unsupervised algorithm. We represent objects as point clouds, a flexible and general representation for 3D data, which we encode into a vector representation. We show that using our method to include context increases the ability of a clustering algorithm to distinguish different semantic classes from each other. Furthermore, we show that our algorithm produces continuous and meaningful object embeddings through interpolation experiments.