Skip to main content

Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13668))

Included in the following conference series:

Abstract

Point clouds and RGB images are two general perceptional sources in autonomous driving. The former can provide accurate localization of objects, and the latter is denser and richer in semantic information. Recently, AutoAlign [6] presents a learnable paradigm in combining these two modalities for 3D object detection. However, it suffers from high computational cost introduced by the global-wise attention. To solve the problem, we propose Cross-Domain DeformCAFA module in this work. It attends to sparse learnable sampling points for cross-modal relational modeling, which enhances the tolerance to calibration error and greatly speeds up the feature aggregation across different modalities. To overcome the complex GT-AUG under multi-modal settings, we design a simple yet effective cross-modal augmentation strategy on convex combination of image patches given their depth information. Moreover, by carrying out a novel image-level dropout training scheme, our model is able to infer in a dynamic manner. To this end, we propose AutoAlignV2, a faster and stronger multi-modal 3D detection framework, built on top of AutoAlign. Extensive experiments on nuScenes benchmark demonstrate the effectiveness and efficiency of AutoAlignV2. Notably, our best model reaches 72.4 NDS on nuScenes test leaderboard, achieving new state-of-the-art results among all published multi-modal 3D object detectors. Code will be available at https://github.com/zehuichen123/AutoAlignV2.

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

References

  1. Bai, X., et al.: TransFusion: robust LiDAR-camera fusion for 3D object detection with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090–1099 (2022)

    Google Scholar 

  2. Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 11621–11631 (2020)

    Google Scholar 

  3. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  4. Chen, Q., Sun, L., Cheung, E., Yuille, A.L.: Every view counts: cross-view consistency in 3D object detection with hybrid-cylindrical-spherical voxelization. Adv. Neural Inf. Process. Syst., 21224–21235 (2020)

    Google Scholar 

  5. 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 

  6. Chen, Z., et al.: AutoAlign: pixel-instance feature aggregation for multi-modal 3D object detection. IJCAI, pp. 1–7 (2022)

    Google Scholar 

  7. Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https://github.com/open-mmlab/mmdetection3D (2020)

  8. Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards high performance voxel-based 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1201–1209 (2021)

    Google Scholar 

  9. Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv preprint arXiv:2107.08430, pp. 1–6 (2021)

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

    Google Scholar 

  11. Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: enhancing point features with image semantics for 3d object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 35–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_3

    Chapter  Google Scholar 

  12. Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3D proposal generation and object detection from view aggregation. In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1–8. IEEE (2018)

    Google Scholar 

  13. 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 

  14. Li, Y., et al.: Fully convolutional networks for panoptic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 214–223 (2021)

    Google Scholar 

  15. Li, Y., et al.: DeepFusion: LiDAR-camera deep fusion for multi-modal 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17182–17191 (2022)

    Google Scholar 

  16. Li, Z., et al.: SimIPU: simple 2D image and 3D point cloud unsupervised pre-training for spatial-aware visual representations. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 36, pp. 1500–1508 (2022)

    Google Scholar 

  17. Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Proceedings of the European Conference on Computer Vision, pp. 641–656 (2018)

    Google Scholar 

  18. Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)

    Google Scholar 

  19. Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird’s-eye view representation. arXiv preprint arXiv:2205.13542 (2022)

  20. 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 

  21. Pang, S., Morris, D., Radha, H.: CLOCs: camera-LiDAR object candidates fusion for 3D object detection. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1–10. IEEE (2020)

    Google Scholar 

  22. 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 

  23. Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918–927 (2018)

    Google Scholar 

  24. 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 

  25. Shi, S., Wang, X., Li, H.: Point RCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 770–779 (2019)

    Google Scholar 

  26. Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1–14 (2020)

    Google Scholar 

  27. Sindagi, V.A., Zhou, Y., Tuzel, O.: MVX-Net: multimodal VoxelNet for 3D object detection. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 7276–7282. IEEE (2019)

    Google Scholar 

  28. 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 

  29. Vora, S., Lang, A.H., Helou, B., Beijbom, O.: PointPainting: sequential fusion for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604–4612 (2020)

    Google Scholar 

  30. Wang, C.Y., et al.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390–391 (2020)

    Google Scholar 

  31. Wang, C., Ma, C., Zhu, M., Yang, X.: PointAugmenting: cross-modal augmentation for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11794–11803 (2021)

    Google Scholar 

  32. Wang, Y., Solomon, J.M.: Object DGCNN: 3D object detection using dynamic graphs. In: Advances in Neural Information Processing Systems 34 (2021)

    Google Scholar 

  33. Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18, 3337 (2018)

    Article  Google Scholar 

  34. Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040–11048 (2020)

    Google Scholar 

  35. Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: sparse-to-dense 3D object detector for point cloud. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1951–1960 (2019)

    Google Scholar 

  36. 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 

  37. Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3D-CVF: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 720–736. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_43

    Chapter  Google Scholar 

  38. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: MixUp: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, pp. 1–12 (2017)

  39. Zhang, W., Wang, Z., Loy, C.C., Zhang, W.: Improving data augmentation for multi-modality 3D object detection. arXiv preprint arXiv:2012.12741, pp. 1–10 (2021)

  40. 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 

  41. 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 

  42. Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv preprint arXiv:1908.09492, pp. 1–10 (2019)

  43. Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations, pp. 1–12 (2020)

    Google Scholar 

Download references

Acknowledgments

This work was supported by the USTC-NIO Joint Research Funds KD2111180313. We acknowledge the support of GPU cluster built by MCC Lab of Information Science and Technology Institution, USTC.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Feng Zhao .

Editor information

Editors and Affiliations

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

Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F. (2022). Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection. 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 13668. Springer, Cham. https://doi.org/10.1007/978-3-031-20074-8_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20074-8_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20073-1

  • Online ISBN: 978-3-031-20074-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics