mlsanityData to 7 Oct 2026

GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds

arXiv 2212.03010 ↗First posted 6 Dec 2022cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks such as image and video, exploring MAE in large-scale 3D point clouds remains challenging due to the inherent irregularity. In contrast to previous 3D MAE frameworks, which either design a complex decoder to infer masked information from maintained regions or adopt sophisticated masking strategies, we instead propose a much simpler paradigm. The core idea is to apply a Generative Decoder for MAE (GD-MAE) to automatically merges the surrounding context to restore the masked geometric knowledge in a hierarchical fusion manner. In doing so, our approach is free from introducing the heuristic design of decoders and enjoys the flexibility of exploring various masking strategies. The corresponding part costs less than 12% latency compared with conventional methods, while achieving better performance. We demonstrate the efficacy of the proposed method on several large-scale benchmarks: Waymo, KITTI, and ONCE. Consistent improvement on downstream detection tasks illustrates strong robustness and generalization capability. Not only our method reveals state-of-the-art results, but remarkably, we achieve comparable accuracy even with 20% of the labeled data on the Waymo dataset. Code will be released at https://github.com/Nightmare-n/GD-MAE.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 74 of its 85 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

74 of 85 references.

References · 74

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2020Point Transformercited by 1,462
  11. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  12. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
38 more
  1. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  2. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  3. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  6. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  8. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  9. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  10. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  11. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  12. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  13. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  14. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  15. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  16. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  17. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  18. 2021Voxel Transformer for 3D Object Detectioncited by 247
  19. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  20. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  21. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  22. 2021Group-Free 3D Object Detection via Transformerscited by 215
  23. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  24. 20203D Object Detection with Pointformercited by 194
  25. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  26. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  27. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  28. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  29. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  30. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  31. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  32. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  33. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  34. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  35. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  36. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  37. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  38. 2022ConvMAE: Masked Convolution Meets Masked Autoencoderscited by 105

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 18; 2024: 18; 2025: 16; 2026: 4.

57 papers.

Sort:

By area:

  1. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  2. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  3. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  4. 2024Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learningcited by 45
  5. 2023FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxelscited by 34
  6. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  7. 2023BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Cloudscited by 24
  8. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  9. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  10. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  11. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  12. 2023AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Datasetcited by 21
38 more
  1. 2022MAELi: Masked Autoencoder for Large-Scale LiDAR Point Cloudscited by 20
  2. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  3. 2024MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoderscited by 15
  4. 2024Commonsense Prototype for Outdoor Unsupervised 3D Object Detectioncited by 13
  5. 2023UniM2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Drivingcited by 12
  6. 2023T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learningcited by 11
  7. 2024CooPre: Cooperative Pretraining for V2X Cooperative Perceptioncited by 11
  8. 2025Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understandingcited by 10
  9. 2025TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Predictioncited by 9
  10. 2024Data-efficient Event Camera Pre-training via Disentangled Masked Modelingcited by 8
  11. 2023PRED: Pre-training via Semantic Rendering on LiDAR Point Cloudscited by 7
  12. 2025Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Cloudscited by 7
  13. 2024Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Promptscited by 6
  14. 2023SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representationscited by 5
  15. 2024Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensingcited by 5
  16. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  17. 2026Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Cloudscited by 4
  18. 2023Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMScited by 3
  19. 2024Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detectioncited by 3
  20. 2024Scale Disparity of Instances in Interactive Point Cloud Segmentationcited by 3
  21. 2025Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learningcited by 3
  22. 2025Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challengescited by 3
  23. 2024TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perceptioncited by 2
  24. 2025JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Datacited by 2
  25. 2025Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Imagescited by 2
  26. 2025Masked Clustering Prediction for Unsupervised Point Cloud Pre-trainingcited by 2
  27. 2024Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selectioncited by 1
  28. 2024Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perceptioncited by 1
  29. 2024Exploring the Untouched Sweeps for Conflict-Aware 3D Segmentation Pretrainingcited by 1
  30. 2024Point Cloud Unsupervised Pre-training via 3D Gaussian Splattingcited by 1
  31. 2024CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learningcited by 1
  32. 2025Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenizationcited by 1
  33. 2025Exploring Semantic Masked Autoencoder for Self-supervised Point Cloud Understandingcited by 1
  34. 2025Enhancing LiDAR Point Features with Foundation Model Priors for 3D Object Detectioncited by 1
  35. 2025DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learningcited by 1
  36. 2026Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removalcited by 1
  37. 2026GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structurecited by 1
  38. 2023R2Det: Redemption from Range-view for Accurate 3D Object Detectioncited by 0

50 most cited of 57 All 57 (JSON)