# GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training

arXiv: https://arxiv.org/abs/2305.08808 · HTML: https://mlsanity.com/paper/2305.08808/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 64 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 30 of 47)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)

## Built on by (most cited first, 30 of 38)

- [UniPAD: A Universal Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2310.08370/) (2023)
- [Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders](https://mlsanity.com/paper/2312.10726/) (2023)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities](https://mlsanity.com/paper/2401.08045/) (2024)
- [Utonia: Toward One Encoder for All Point Clouds](https://mlsanity.com/paper/2603.03283/) (2026)
- [Masked Modeling for Self-supervised Representation Learning on Vision and Beyond](https://mlsanity.com/paper/2401.00897/) (2023)
- [UniM2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving](https://mlsanity.com/paper/2308.10421/) (2023)
- [Pre-training with Random Orthogonal Projection Image Modeling](https://mlsanity.com/paper/2310.18737/) (2023)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning](https://mlsanity.com/paper/2312.10217/) (2023)
- [CooPre: Cooperative Pretraining for V2X Cooperative Perception](https://mlsanity.com/paper/2408.11241/) (2024)
- [Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2504.19500/) (2025)
- [Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection](https://mlsanity.com/paper/2406.10115/) (2024)
- [TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction](https://mlsanity.com/paper/2508.04682/) (2025)
- [MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning](https://mlsanity.com/paper/2403.08760/) (2024)
- [Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds](https://mlsanity.com/paper/2502.20316/) (2025)
- [Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities](https://mlsanity.com/paper/2509.08302/) (2025)
- [MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis](https://mlsanity.com/paper/2403.00206/) (2024)
- [Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point Clouds](https://mlsanity.com/paper/2409.06827/) (2024)
- [Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds](https://mlsanity.com/paper/2603.25165/) (2026)
- [Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving](https://mlsanity.com/paper/2402.15583/) (2024)
- [Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers](https://mlsanity.com/paper/2502.14142/) (2025)
- [PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Network](https://mlsanity.com/paper/2404.10263/) (2024)
- [Exploring the Untouched Sweeps for Conflict-Aware 3D Segmentation Pretraining](https://mlsanity.com/paper/2407.07465/) (2024)
- [Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting](https://mlsanity.com/paper/2411.18667/) (2024)
- [LiSu: A Dataset and Method for LiDAR Surface Normal Estimation](https://mlsanity.com/paper/2503.08601/) (2025)
- [Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenization](https://mlsanity.com/paper/2505.18819/) (2025)
- [Exploring Semantic Masked Autoencoder for Self-supervised Point Cloud Understanding](https://mlsanity.com/paper/2506.21957/) (2025)
- [Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens](https://mlsanity.com/paper/2603.24327/) (2026)
- [Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal](https://mlsanity.com/paper/2603.28224/) (2026)

## Abstract (arXiv)

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud representation learning framework, based on geometric feature reconstruction. In contrast to recent papers that directly adopt masked autoencoder (MAE) and only predict original coordinates or occupancy from masked point clouds, our method revisits differences between images and point clouds and identifies three self-supervised learning objectives peculiar to point clouds, namely centroid prediction, normal estimation, and curvature prediction. Combined with occupancy prediction, these four objectives yield an nontrivial self-supervised learning task and mutually facilitate models to better reason fine-grained geometry of point clouds. Our pipeline is conceptually simple and it consists of two major steps: first, it randomly masks out groups of points, followed by a Transformer-based point cloud encoder; second, a lightweight Transformer decoder predicts centroid, normal, and curvature for points in each voxel. We transfer the pre-trained Transformer encoder to a downstream peception model. On the nuScene Datset, our model achieves 3.38 mAP improvment for object detection, 2.1 mIoU gain for segmentation, and 1.7 AMOTA gain for multi-object tracking. We also conduct experiments on the Waymo Open Dataset and achieve significant performance improvements over baselines as well.