# Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2409.06827 · HTML: https://mlsanity.com/paper/2409.06827/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Efficient Self-supervised Vision Transformers for Representation Learning](https://mlsanity.com/paper/2106.09785/) (2021)
- [Pillar-based Object Detection for Autonomous Driving](https://mlsanity.com/paper/2007.10323/) (2020)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders](https://mlsanity.com/paper/2206.09900/) (2022)
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/2305.04925/) (2023)
- [ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals](https://mlsanity.com/paper/2303.12071/) (2023)
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://mlsanity.com/paper/2104.08683/) (2021)
- [ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2207.12654/) (2022)
- [DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2309.15109/) (2023)
- [GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training](https://mlsanity.com/paper/2305.08808/) (2023)
- [BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios](https://mlsanity.com/paper/2212.05758/) (2022)
- [MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds](https://mlsanity.com/paper/2212.07207/) (2022)
- [Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving](https://mlsanity.com/paper/2306.07276/) (2023)

## Built on by (most cited first, 4 of 4)

- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers](https://mlsanity.com/paper/2502.14142/) (2025)
- [UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition](https://mlsanity.com/paper/2601.05105/) (2026)
- [TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation](https://mlsanity.com/paper/2607.10762/) (2026)

## Abstract (arXiv)

3D perception in LiDAR point clouds is crucial for a self-driving vehicle to properly act in 3D environment. However, manually labeling point clouds is hard and costly. There has been a growing interest in self-supervised pre-training of 3D perception models. Following the success of contrastive learning in images, current methods mostly conduct contrastive pre-training on point clouds only. Yet an autonomous driving vehicle is typically supplied with multiple sensors including cameras and LiDAR. In this context, we systematically study single modality, cross-modality, and multi-modality for contrastive learning of point clouds, and show that cross-modality wins over other alternatives. In addition, considering the huge difference between the training sources in 2D images and 3D point clouds, it remains unclear how to design more effective contrastive units for LiDAR. We therefore propose the instance-aware and similarity-balanced contrastive units that are tailored for self-driving point clouds. Extensive experiments reveal that our approach achieves remarkable performance gains over various point cloud models across the downstream perception tasks of LiDAR based 3D object detection and 3D semantic segmentation on the four popular benchmarks including Waymo Open Dataset, nuScenes, SemanticKITTI and ONCE.