Skip to main content

LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13681))

Included in the following conference series:

Abstract

Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving. However, arguably due to the higher-dimensional nature of the data (as compared to images), existing neural architectures exhibit a large variety in their designs, including but not limited to the views considered, the format of the neural features, and the neural operations used. Lack of a unified framework and interpretation makes it hard to put these designs in perspective, as well as systematically explore new ones. In this paper, we begin by proposing a unified framework of such, with the key idea being factorizing the neural networks into a series of view transforms and neural layers. We demonstrate that this modular framework can reproduce a variety of existing works while allowing a fair comparison of backbone designs. Then, we show how this framework can easily materialize into a concrete neural architecture search (NAS) space, allowing a principled NAS-for-3D exploration. In performing evolutionary NAS on the 3D object detection task on the Waymo Open Dataset, not only do we outperform the state-of-the-art models, but also report the interesting finding that NAS tends to discover the same macro-level architecture concept for both the vehicle and pedestrian classes.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    We empirically picked these multipliers; did not tune them heavily.

  2. 2.

    We skipped PointPillars-like pedestrian, because the corresponding number in Table 1 is yellow not green.

  3. 3.

    In fact this architecture was sampled/discovered during our evolution.

References

  1. Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)

  2. Bae, W., Lee, S., Lee, Y., Park, B., Chung, M., Jung, K.-H.: Resource optimized neural architecture search for 3D medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 228–236. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_26

    Chapter  Google Scholar 

  3. Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. arXiv preprint arXiv:1611.02167 (2016)

  4. Bender, G., et al.: Can weight sharing outperform random architecture search? an investigation with tunas. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14323–14332 (2020)

    Google Scholar 

  5. Bewley, A., Sun, P., Mensink, T., Anguelov, D., Sminchisescu, C.: Range conditioned dilated convolutions for scale invariant 3d object detection. arXiv preprint arXiv:2005.09927 (2020)

  6. Chai, Y., et al.: To the point: efficient 3d object detection in the range image with graph convolution kernels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000–16009 (2021)

    Google Scholar 

  7. Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. arXiv preprint arXiv:1809.04184 (2018)

  8. Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1907–1915 (2017)

    Google Scholar 

  9. Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards high performance voxel-based 3d object detection. arXiv preprint arXiv:2012.15712 (2020)

  10. Engel, N., Belagiannis, V., Dietmayer, K.: Point transformer. IEEE Access 9, 134826–134840 (2021)

    Article  Google Scholar 

  11. Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1355–1361. IEEE (2017)

    Google Scholar 

  12. Fan, L., Xiong, X., Wang, F., Wang, N., Zhang, Z.: Rangedet: in defense of range view for lidar-based 3d object detection. arXiv preprint arXiv:2103.10039 (2021)

  13. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361. IEEE (2012)

    Google Scholar 

  14. Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019)

    Google Scholar 

  15. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  16. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)

    Google Scholar 

  17. Kim, S., et al.: Scalable neural architecture search for 3D medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 220–228. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_25

    Chapter  Google Scholar 

  18. Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697–12705 (2019)

    Google Scholar 

  19. Li, G., Qian, G., Delgadillo, I.C., Muller, M., Thabet, A., Ghanem, B.: SGAS: sequential greedy architecture search. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1620–1630 (2020)

    Google Scholar 

  20. Li, G., Xu, M., Giancola, S., Thabet, A., Ghanem, B.: LC-NAS: latency constrained neural architecture search for point cloud networks. arXiv preprint arXiv:2008.10309 (2020)

  21. Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search. In: Uncertainty in Artificial Intelligence, pp. 367–377. PMLR (2020)

    Google Scholar 

  22. Liu, C., et al.: Auto-Deeplab: hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 82–92 (2019)

    Google Scholar 

  23. Liu, C., et al.: Progressive neural architecture search. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19–34 (2018)

    Google Scholar 

  24. Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)

  25. Liu, Z., Tang, H., Lin, Y., Han, S.: Point-voxel CNN for efficient 3d deep learning. arXiv preprint arXiv:1907.03739 (2019)

  26. Ma, Z., Zhou, Z., Liu, Y., Lei, Y., Yan, H.: Auto-orvnet: orientation-boosted volumetric neural architecture search for 3d shape classification. IEEE Access 8, 12942–12954 (2019)

    Article  Google Scholar 

  27. Mao, J., et al.: Voxel transformer for 3d object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3164–3173 (2021)

    Google Scholar 

  28. Meyer, G.P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., Wellington, C.K.: Lasernet: an efficient probabilistic 3d object detector for autonomous driving. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12677–12686 (2019)

    Google Scholar 

  29. Ngiam, J., et al.: Starnet: targeted computation for object detection in point clouds. arXiv preprint arXiv:1908.11069 (2019)

  30. Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J.: Efficient neural architecture search via parameters sharing. In: International Conference on Machine Learning, pp. 4095–4104. PMLR (2018)

    Google Scholar 

  31. Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9277–9286 (2019)

    Google Scholar 

  32. Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)

    Google Scholar 

  33. Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413 (2017)

  34. Qi, C.R., et al.: Offboard 3D object detection from point cloud sequences. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6134–6144 (2021)

    Google Scholar 

  35. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4780–4789 (2019)

    Google Scholar 

  36. Real, E., et al.: Large-scale evolution of image classifiers. In: International Conference on Machine Learning, pp. 2902–2911. PMLR (2017)

    Google Scholar 

  37. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  38. Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529–10538 (2020)

    Google Scholar 

  39. Shi, S., Guo, C., Yang, J., Li, H.: PV-RCNN: the top-performing lidar-only solutions for 3D detection/3d tracking/domain adaptation of waymo open dataset challenges. arXiv preprint arXiv:2008.12599 (2020)

  40. So, D., Le, Q., Liang, C.: The evolved transformer. In: International Conference on Machine Learning, pp. 5877–5886. PMLR (2019)

    Google Scholar 

  41. So, D.R., Mańke, W., Liu, H., Dai, Z., Shazeer, N., Le, Q.V.: Primer: searching for efficient transformers for language modeling. arXiv preprint arXiv:2109.08668 (2021)

  42. Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446–2454 (2020)

    Google Scholar 

  43. Sun, P., et al.: RSN: range sparse net for efficient, accurate lidar 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5725–5734 (2021)

    Google Scholar 

  44. Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)

    Google Scholar 

  45. Tang, H., et al.: Searching efficient 3D architectures with sparse point-voxel convolution. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 685–702. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58604-1_41

    Chapter  Google Scholar 

  46. Wang, Y., et al.: Pillar-based object detection for autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 18–34. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58542-6_2

    Chapter  Google Scholar 

  47. Wong, K.C.L., Moradi, M.: SegNAS3D: network architecture search with derivative-free global optimization for 3D image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 393–401. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_44

    Chapter  Google Scholar 

  48. Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-FPN: automatic network architecture adaptation for object detection beyond classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6649–6658 (2019)

    Google Scholar 

  49. Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)

    Article  Google Scholar 

  50. Yang, B., Luo, W., Urtasun, R.: Pixor: Real-time 3d object detection from point clouds. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 7652–7660 (2018)

    Google Scholar 

  51. Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784–11793 (2021)

    Google Scholar 

  52. Yu, Q., et al.: C2FNAS: coarse-to-fine neural architecture search for 3D medical image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4126–4135 (2020)

    Google Scholar 

  53. Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16259–16268 (2021)

    Google Scholar 

  54. Zhou, Y., et al.: End-to-end multi-view fusion for 3D object detection in lidar point clouds. In: Conference on Robot Learning, pp. 923–932. PMLR (2020)

    Google Scholar 

  55. Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490–4499 (2018)

    Google Scholar 

  56. Zhu, Z., Liu, C., Yang, D., Yuille, A., Xu, D.: V-NAS: neural architecture search for volumetric medical image segmentation. In: 2019 International Conference on 3D Vision (3DV), pp. 240–248. IEEE (2019)

    Google Scholar 

  57. Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Chenxi Liu .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 157 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liu, C. et al. (2022). LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13681. Springer, Cham. https://doi.org/10.1007/978-3-031-19803-8_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19803-8_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19802-1

  • Online ISBN: 978-3-031-19803-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics