# Unsupervised Point Cloud Pre-Training via Contrasting and Clustering

arXiv: https://arxiv.org/abs/2202.02543 · HTML: https://mlsanity.com/paper/2202.02543/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 5 Feb 2022.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [Multiresolution Tree Networks for 3D Point Cloud Processing](https://mlsanity.com/paper/1807.03520/) (2018)
- [Unsupervised Multi-Task Feature Learning on Point Clouds](https://mlsanity.com/paper/1910.08207/) (2019)
- [Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds](https://mlsanity.com/paper/2003.12971/) (2020)
- [Self-supervised Learning of Point Clouds via Orientation Estimation](https://mlsanity.com/paper/2008.00305/) (2020)
- [Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning](https://mlsanity.com/paper/2006.02598/) (2020)
- [Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction](https://mlsanity.com/paper/1907.12704/) (2019)
- [RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion](https://mlsanity.com/paper/1904.12304/) (2019)
- [VConv-DAE: Deep Volumetric Shape Learning Without Object Labels](https://mlsanity.com/paper/1604.03755/) (2016)
- [Geometry Sharing Network for 3D Point Cloud Classification and Segmentation](https://mlsanity.com/paper/1912.10644/) (2019)

## Built on by (most cited first, 9 of 9)

- [CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training](https://mlsanity.com/paper/2210.01055/) (2022)
- [Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey](https://mlsanity.com/paper/2305.04691/) (2023)
- [Rethinking the compositionality of point clouds through regularization in the hyperbolic space](https://mlsanity.com/paper/2209.10318/) (2022)
- [PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering](https://mlsanity.com/paper/2304.08965/) (2023)
- [3D CoCa: Contrastive Learners are 3D Captioners](https://mlsanity.com/paper/2504.09518/) (2025)
- [Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2211.06841/) (2022)
- [SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data](https://mlsanity.com/paper/2308.05410/) (2023)
- [3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence](https://mlsanity.com/paper/2601.06496/) (2026)
- [PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer](https://mlsanity.com/paper/2512.03111/) (2025)

## Abstract (arXiv)

Annotating large-scale point clouds is highly time-consuming and often infeasible for many complex real-world tasks. Point cloud pre-training has therefore become a promising strategy for learning discriminative representations without labeled data. In this paper, we propose a general unsupervised pre-training framework, termed ConClu, which jointly integrates contrasting and clustering. The contrasting objective maximizes the similarity between feature representations extracted from two augmented views of the same point cloud, while the clustering objective simultaneously partitions the data and enforces consistency between cluster assignments across augmentations. Experimental results on multiple downstream tasks show that our method outperforms state-of-the-art approaches, demonstrating the effectiveness of the proposed framework. Code is available at https://github.com/gfmei/conclu.