Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders (2206.09900v7)

Published 20 Jun 2022 in cs.CV

Abstract: Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE). While existing masked point autoencoding methods mainly focus on small-scale indoor point clouds or pillar-based large-scale outdoor LiDAR data, our approach introduces a new self-supervised masked occupancy pre-training method called Occupancy-MAE, specifically designed for voxel-based large-scale outdoor LiDAR point clouds. Occupancy-MAE takes advantage of the gradually sparse voxel occupancy structure of outdoor LiDAR point clouds and incorporates a range-aware random masking strategy and a pretext task of occupancy prediction. By randomly masking voxels based on their distance to the LiDAR and predicting the masked occupancy structure of the entire 3D surrounding scene, Occupancy-MAE encourages the extraction of high-level semantic information to reconstruct the masked voxel using only a small number of visible voxels. Extensive experiments demonstrate the effectiveness of Occupancy-MAE across several downstream tasks. For 3D object detection, Occupancy-MAE reduces the labelled data required for car detection on the KITTI dataset by half and improves small object detection by approximately 2% in AP on the Waymo dataset. For 3D semantic segmentation, Occupancy-MAE outperforms training from scratch by around 2% in mIoU. For multi-object tracking, Occupancy-MAE enhances training from scratch by approximately 1% in terms of AMOTA and AMOTP. Codes are publicly available at https://github.com/chaytonmin/Occupancy-MAE.

PDF HTML Abstract

An Expert Overview of "Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders"

The paper "Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders" introduces a significant advancement in self-supervised learning for LiDAR-based 3D perception, specifically designed for autonomous driving applications. The central proposition is the Occupancy-MAE, a novel self-supervised framework leveraging masked autoencoders to pre-train models on large-scale unlabeled outdoor LiDAR point clouds. This approach addresses the challenge of dependence on extensive labeled 3D datasets, which are costly and time-consuming to annotate.

In essence, the methodology introduced pivots around a masked autoencoding strategy, targeted particularly at the voxel-based representation of LiDAR data. The paper acknowledges the limitations of existing masked point autoencoding methodologies, which have predominantly catered to small-scale indoor point clouds or pillar-based representations. Occupancy-MAE differentiates itself by adopting a voxel-based approach, which more accurately reflects the sparse structural characteristics encountered in real-world LiDAR data used for autonomous vehicles.

Methodological Innovations

Occupancy-MAE introduces a self-supervised masked occupancy pre-training method that hinges on three key components:

  1. Masked Autoencoders (MAE): The framework employs masked autoencoders as a pre-training strategy to extract high-level semantic information by reconstructing the masked occupancy structure of the LiDAR point clouds. This marks a departure from earlier methods that focused merely on reconstructing individual points.
  2. Range-aware Random Masking Strategy: Traditional random masking approaches are transcended by a novel method that considers the varying density of LiDAR data points based on their distance from the sensor. This enhances training efficacy by optimizing the masking strategy based on spatial voxel sparsity.
  3. 3D Occupancy Prediction: Unlike existing methods that emphasize point regression, Occupancy-MAE introduces occupancy prediction as the pretext task. This task involves predicting the occupancy status of voxels, encouraging the learning of robust and representative features for 3D perception tasks.

Experimental Validation

The paper presents extensive experimental results across various datasets such as ONCE, KITTI, Waymo, and nuScenes. The results substantiate that Occupancy-MAE offers substantial performance improvements across several downstream tasks. Specifically, for 3D object detection, it significantly reduces the labeled data requirement for car detection in the KITTI dataset and improves small object detection accuracy in the Waymo dataset. It also consistently outperforms models trained from scratch in 3D semantic segmentation and multi-object tracking tasks, with evident improvements in metrics such as mIoU, AMOTA, and AMOTP.

Implications and Future Directions

The implications of Occupancy-MAE extend both practically and theoretically. Practically, the framework enhances the data efficiency of 3D perception models, a critical advancement considering the high cost associated with annotating large-scale 3D datasets. This capability is particularly significant for autonomous driving systems, where data scarcity and high annotation costs pose substantial barriers.

Theoretically, the introduction of occupancy prediction as a pretext task invites further exploration into how 3D structures are semantically understood by neural networks. The method’s ability to generalize across different downstream tasks and datasets suggests a robustness that could be foundational for future research in self-supervised learning paradigms, not merely limited to autonomous driving.

Moving forward, research could branch into pre-training with high-resolution data and understanding temporal sequences in LiDAR point clouds. Furthermore, adapting this methodology to incorporate dynamic scene understanding through multi-frame fusion and extending it across diversified large-scale datasets might unlock newer dimensions in autonomous perception.

The open availability of the Occupancy-MAE code promises to catalyze further research and application of this framework, potentially setting a new benchmark in the self-supervised learning methodology for LiDAR-based 3D perception.

File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. J. Liu, W. Xiong, L. Bai, Y. Xia, T. Huang, W. Ouyang, and B. Zhu, “Deep instance segmentation with automotive radar detection points,” IEEE Transactions on Intelligent Vehicles, vol. 8, no. 1, pp. 84–94, 2022.
  2. A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? the kitti vision benchmark suite,” in 2012 IEEE conference on computer vision and pattern recognition.   IEEE, 2012, pp. 3354–3361.
  3. P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine et al., “Scalability in perception for autonomous driving: Waymo open dataset,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2446–2454.
  4. H. Caesar, V. Bankiti, A. H. Lang, S. Vora, V. E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, and O. Beijbom, “nuscenes: A multimodal dataset for autonomous driving,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 621–11 631.
  5. J. Mao, M. Niu, C. Jiang, H. Liang, J. Chen, X. Liang, Y. Li, C. Ye, W. Zhang, Z. Li et al., “One million scenes for autonomous driving: Once dataset,” arXiv preprint arXiv:2106.11037, 2021.
  6. Y. Yan, Y. Mao, and B. Li, “Second: Sparsely embedded convolutional detection,” Sensors, vol. 18, no. 10, p. 3337, 2018.
  7. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
  8. K. He, X. Chen, S. Xie, Y. Li, P. Dollár, and R. Girshick, “Masked autoencoders are scalable vision learners,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16 000–16 009.
  9. X. Chen, M. Ding, X. Wang, Y. Xin, S. Mo, Y. Wang, S. Han, P. Luo, G. Zeng, and J. Wang, “Context autoencoder for self-supervised representation learning,” arXiv preprint arXiv:2202.03026, 2022.
  10. Z. Xie, Z. Zhang, Y. Cao, Y. Lin, J. Bao, Z. Yao, Q. Dai, and H. Hu, “Simmim: A simple framework for masked image modeling,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9653–9663.
  11. Y. Pang, W. Wang, F. E. Tay, W. Liu, Y. Tian, and L. Yuan, “Masked autoencoders for point cloud self-supervised learning,” arXiv preprint arXiv:2203.06604, 2022.
  12. X. Yu, L. Tang, Y. Rao, T. Huang, J. Zhou, and J. Lu, “Point-bert: Pre-training 3d point cloud transformers with masked point modeling,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19 313–19 322.
  13. H. Liu, M. Cai, and Y. J. Lee, “Masked discrimination for self-supervised learning on point clouds,” arXiv preprint arXiv:2203.11183, 2022.
  14. R. Zhang, Z. Guo, P. Gao, R. Fang, B. Zhao, D. Wang, Y. Qiao, and H. Li, “Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training,” arXiv preprint arXiv:2205.14401, 2022.
  15. A. X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su et al., “Shapenet: An information-rich 3d model repository,” arXiv preprint arXiv:1512.03012, 2015.
  16. A. Dai, A. X. Chang, M. Savva, M. Halber, T. Funkhouser, and M. Nießner, “Scannet: Richly-annotated 3d reconstructions of indoor scenes,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 5828–5839.
  17. C. Xu, B. Wu, Z. Wang, W. Zhan, P. Vajda, K. Keutzer, and M. Tomizuka, “Squeezesegv3: Spatially-adaptive convolution for efficient point-cloud segmentation,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVIII 16.   Springer, 2020, pp. 1–19.
  18. X. Zhu, H. Zhou, T. Wang, F. Hong, Y. Ma, W. Li, H. Li, and D. Lin, “Cylindrical and asymmetrical 3d convolution networks for lidar segmentation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 9939–9948.
  19. S. Xie, J. Gu, D. Guo, C. R. Qi, L. Guibas, and O. Litany, “Pointcontrast: Unsupervised pre-training for 3d point cloud understanding,” in European conference on computer vision.   Springer, 2020, pp. 574–591.
  20. X. Li, H. Ding, W. Zhang, H. Yuan, J. Pang, G. Cheng, K. Chen, Z. Liu, and C. C. Loy, “Transformer-based visual segmentation: A survey,” arXiv preprint arXiv:2304.09854, 2023.
  21. M.-H. Guo, J.-X. Cai, Z.-N. Liu, T.-J. Mu, R. R. Martin, and S.-M. Hu, “Pct: Point cloud transformer,” Computational Visual Media, vol. 7, pp. 187–199, 2021.
  22. X. Yan, C. Zheng, Z. Li, S. Wang, and S. Cui, “Pointasnl: Robust point clouds processing using nonlocal neural networks with adaptive sampling,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 5589–5598.
  23. J. Mao, Y. Xue, M. Niu, H. Bai, J. Feng, X. Liang, H. Xu, and C. Xu, “Voxel transformer for 3d object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3164–3173.
  24. C. He, R. Li, S. Li, and L. Zhang, “Voxel set transformer: A set-to-set approach to 3d object detection from point clouds,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8417–8427.
  25. L. Fan, Z. Pang, T. Zhang, Y.-X. Wang, H. Zhao, F. Wang, N. Wang, and Z. Zhang, “Embracing single stride 3d object detector with sparse transformer,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8458–8468.
  26. Z. Liu, X. Yang, H. Tang, S. Yang, and S. Han, “Flatformer: Flattened window attention for efficient point cloud transformer,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1200–1211.
  27. G. Hess, J. Jaxing, E. Svensson, D. Hagerman, C. Petersson, and L. Svensson, “Masked autoencoder for self-supervised pre-training on lidar point clouds,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 350–359.
  28. R. Xu, T. Wang, W. Zhang, R. Chen, J. Cao, J. Pang, and D. Lin, “Mv-jar: Masked voxel jigsaw and reconstruction for lidar-based self-supervised pre-training,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13 445–13 454.
  29. X. Tian, H. Ran, Y. Wang, and H. Zhao, “Geomae: Masked geometric target prediction for self-supervised point cloud pre-training,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13 570–13 580.
  30. H. Yang, T. He, J. Liu, H. Chen, B. Wu, B. Lin, X. He, and W. Ouyang, “Gd-mae: generative decoder for mae pre-training on lidar point clouds,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9403–9414.
  31. A. H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, and O. Beijbom, “Pointpillars: Fast encoders for object detection from point clouds,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 12 697–12 705.
  32. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  33. A. Elfes, “Using occupancy grids for mobile robot perception and navigation,” Computer, vol. 22, no. 6, pp. 46–57, 1989.
  34. H. Fu, H. Xue, and R. Ren, “Fast implementation of 3d occupancy grid for autonomous driving,” in 2020 12th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), vol. 2.   IEEE, 2020, pp. 217–220.
  35. R. Mahjourian, J. Kim, Y. Chai, M. Tan, B. Sapp, and D. Anguelov, “Occupancy flow fields for motion forecasting in autonomous driving,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 5639–5646, 2022.
  36. S. Hoermann, M. Bach, and K. Dietmayer, “Dynamic occupancy grid prediction for urban autonomous driving: A deep learning approach with fully automatic labeling,” in 2018 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2018, pp. 2056–2063.
  37. X. Sun, S. Wang, M. Wang, Z. Wang, and M. Liu, “A novel coding architecture for lidar point cloud sequence,” IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 5637–5644, 2020.
  38. C. Tu, E. Takeuchi, A. Carballo, and K. Takeda, “Point cloud compression for 3d lidar sensor using recurrent neural network with residual blocks,” in 2019 International Conference on Robotics and Automation (ICRA).   IEEE, 2019, pp. 3274–3280.
  39. X. Sun, H. Ma, Y. Sun, and M. Liu, “A novel point cloud compression algorithm based on clustering,” IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 2132–2139, 2019.
  40. Y. Feng, S. Liu, and Y. Zhu, “Real-time spatio-temporal lidar point cloud compression,” in 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS).   IEEE, 2020, pp. 10 766–10 773.
  41. S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang, and H. Li, “Pv-rcnn: Point-voxel feature set abstraction for 3d object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10 529–10 538.
  42. T. Yin, X. Zhou, and P. Krahenbuhl, “Center-based 3d object detection and tracking,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11 784–11 793.
  43. S. Shi, L. Jiang, J. Deng, Z. Wang, C. Guo, J. Shi, X. Wang, and H. Li, “Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection,” arXiv preprint arXiv:2102.00463, 2021.
  44. B. Zhang, J. Yuan, B. Shi, T. Chen, Y. Li, and Y. Qiao, “Uni3d: A unified baseline for multi-dataset 3d object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9253–9262.
  45. J. Yuan, B. Zhang, X. Yan, T. Chen, B. Shi, Y. Li, and Y. Qiao, “Ad-pt: Autonomous driving pre-training with large-scale point cloud dataset,” arXiv preprint arXiv:2306.00612, 2023.
  46. S. Shi, X. Wang, and H. Li, “Pointrcnn: 3d object proposal generation and detection from point cloud,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 770–779.
  47. Z. Yang, Y. Sun, S. Liu, and J. Jia, “3dssd: Point-based 3d single stage object detector,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 040–11 048.
  48. Y. Zhou and O. Tuzel, “Voxelnet: End-to-end learning for point cloud based 3d object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4490–4499.
  49. Y. Chen, S. Liu, X. Shen, and J. Jia, “Fast point r-cnn,” in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 9775–9784.
  50. C. R. Qi, H. Su, K. Mo, and L. J. Guibas, “Pointnet: Deep learning on point sets for 3d classification and segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 652–660.
  51. B. Wu, A. Wan, X. Yue, and K. Keutzer, “Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud,” in 2018 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2018, pp. 1887–1893.
  52. A. Milioto, I. Vizzo, J. Behley, and C. Stachniss, “Rangenet++: Fast and accurate lidar semantic segmentation,” in 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS).   IEEE, 2019, pp. 4213–4220.
  53. H. Tang, Z. Liu, S. Zhao, Y. Lin, J. Lin, H. Wang, and S. Han, “Searching efficient 3d architectures with sparse point-voxel convolution,” in European conference on computer vision.   Springer, 2020, pp. 685–702.
  54. C. Doersch, A. Gupta, and A. A. Efros, “Unsupervised visual representation learning by context prediction,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1422–1430.
  55. S. Gidaris, P. Singh, and N. Komodakis, “Unsupervised representation learning by predicting image rotations,” arXiv preprint arXiv:1803.07728, 2018.
  56. J. Xu, L. Xiao, and A. M. López, “Self-supervised domain adaptation for computer vision tasks,” IEEE Access, vol. 7, pp. 156 694–156 706, 2019.
  57. L. Xiao, J. Xu, D. Zhao, Z. Wang, L. Wang, Y. Nie, and B. Dai, “Self-supervised domain adaptation with consistency training,” in 2020 25th International Conference on Pattern Recognition (ICPR).   IEEE, 2021, pp. 6874–6880.
  58. F. M. Carlucci, A. D’Innocente, S. Bucci, B. Caputo, and T. Tommasi, “Domain generalization by solving jigsaw puzzles,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2229–2238.
  59. M. Caron, P. Bojanowski, A. Joulin, and M. Douze, “Deep clustering for unsupervised learning of visual features,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 132–149.
  60. M. Caron, I. Misra, J. Mairal, P. Goyal, P. Bojanowski, and A. Joulin, “Unsupervised learning of visual features by contrasting cluster assignments,” Advances in Neural Information Processing Systems, vol. 33, pp. 9912–9924, 2020.
  61. K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, “Momentum contrast for unsupervised visual representation learning,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 9729–9738.
  62. J.-B. Grill, F. Strub, F. Altché, C. Tallec, P. Richemond, E. Buchatskaya, C. Doersch, B. Avila Pires, Z. Guo, M. Gheshlaghi Azar et al., “Bootstrap your own latent-a new approach to self-supervised learning,” Advances in neural information processing systems, vol. 33, pp. 21 271–21 284, 2020.
  63. J. Yin, D. Zhou, L. Zhang, J. Fang, C.-Z. Xu, J. Shen, and W. Wang, “Proposalcontrast: Unsupervised pre-training for lidar-based 3d object detection,” in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXIX.   Springer, 2022, pp. 17–33.
  64. Z. Zhang, R. Girdhar, A. Joulin, and I. Misra, “Self-supervised pretraining of 3d features on any point-cloud,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10 252–10 263.
  65. Z. Tong, Y. Song, J. Wang, and L. Wang, “Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training,” arXiv preprint arXiv:2203.12602, 2022.
  66. A. Boulch, C. Sautier, B. Michele, G. Puy, and R. Marlet, “Also: Automotive lidar self-supervision by occupancy estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13 455–13 465.
  67. Z. Zhang, M. Bai, and E. Li, “Implicit surface contrastive clustering for lidar point clouds,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 21 716–21 725.
  68. B. Graham, M. Engelcke, and L. Van Der Maaten, “3d semantic segmentation with submanifold sparse convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 9224–9232.
  69. J. Yang, S. Shi, Z. Wang, H. Li, and X. Qi, “St3d: Self-training for unsupervised domain adaptation on 3d object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10 368–10 378.
  70. O. D. Team, “Openpcdet: An open-source toolbox for 3d object detection from point clouds,” https://github.com/open-mmlab/OpenPCDet, 2020.
  71. H. Liang, C. Jiang, D. Feng, X. Chen, H. Xu, X. Liang, W. Zhang, Z. Li, and L. Van Gool, “Exploring geometry-aware contrast and clustering harmonization for self-supervised 3d object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3293–3302.
  72. Z. Lin and Y. Wang, “Bev-mae: Bird’s eye view masked autoencoders for outdoor point cloud pre-training,” arXiv preprint arXiv:2212.05758, 2022.
  73. J. Liu, L. Bai, Y. Xia, T. Huang, B. Zhu, and Q.-L. Han, “Gnn-pmb: A simple but effective online 3d multi-object tracker without bells and whistles,” IEEE Transactions on Intelligent Vehicles, vol. 8, no. 2, pp. 1176–1189, 2022.
  74. Y. Wang, X. Chen, Y. You, L. E. Li, B. Hariharan, M. Campbell, K. Q. Weinberger, and W.-L. Chao, “Train in germany, test in the usa: Making 3d object detectors generalize,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 713–11 723.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Chen Min (17 papers)
  2. Xinli Xu (17 papers)
  3. Dawei Zhao (22 papers)
  4. Liang Xiao (80 papers)
  5. Yiming Nie (9 papers)
  6. Bin Dai (60 papers)
Citations (39)
View on Semantic Scholar