Abstract
Direct detection of 3D objects from point clouds is a challenging task due to sparsity and irregularity of point clouds. To capture point features from the raw point clouds for 3D object detection, most previous researches utilize PointNet and its variants as the feature learning backbone and have seen encouraging results. However, these methods capture point features independently without modeling the interaction between points, and simple symmetric functions cannot adequately aggregate local contextual features, which are vital for 3D object recognition. To address such limitations, we propose ReAGFormer, a reaggregation Transformer backbone with affine group features for point feature learning in 3D object detection, which can capture the dependencies between points on the aligned group feature space while retaining the flexible receptive fields. The key idea of ReAGFormer is to alleviate the perturbation of the point feature space by affine transformation and extract the dependencies between points using self-attention, while reaggregating the local point set features with the learned attention. Moreover, we also design multi-scale connections in the feature propagation layer to reduce the geometric information loss caused by point sampling and interpolation. Experimental results show that by equipping our method as the backbone for existing 3D object detectors, significant improvements and state-of-the-art performance are achieved over original models on SUN RGB-D and ScanNet V2 benchmarks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: CVPR, pp. 1907–1915 (2017)
Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D object detection. In: CVPR, pp. 4490–4499 (2018)
Song, S., Xiao, J.: Deep sliding shapes for amodal 3D object detection in RGB-D images. In: CVPR, pp. 808–816 (2016)
Yang, B., Luo, W., Urtasun, R.: Pixor: real-time 3D object detection from point clouds. In: CVPR, pp. 7652–7660 (2018)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: CVPR, pp. 652–660 (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. NeurIPS 30, 5099–5108 (2017)
Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: ICCV, pp. 9277–9286 (2019)
Xie, Q., et al.: Mlcvnet: multi-level context votenet for 3D object detection. In: CVPR, pp. 10447–10456 (2020)
Zhang, Z., Sun, B., Yang, H., Huang, Q.: H3DNet: 3D object detection using hybrid geometric primitives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 311–329. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_19
Cheng, B., Sheng, L., Shi, S., Yang, M., Xu, D.: Back-tracing representative points for voting-based 3D object detection in point clouds. In: CVPR, pp. 8963–8972 (2021)
Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: ICCV (2021)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998–6008 (2017)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
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
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)
Liu, Y., et al.: A survey of visual transformers. arXiv preprint arXiv:2111.06091 (2021)
Guo, M.H., Cai, J.X., Liu, Z.N., Mu, T.J., Martin, R.R., Hu, S.M.: PCT: point cloud transformer. Comput. Vis. Media 7(2), 187–199 (2021)
Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V.: Point transformer. arXiv preprint arXiv:2012.09164 (2020)
Pan, X., Xia, Z., Song, S., Li, L.E., Huang, G.: 3D object detection with pointformer. In: CVPR, pp. 7463–7472 (2021)
Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR, pp. 5828–5839 (2017)
Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: CVPR, pp. 567–576 (2015)
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: ICCV, pp. 945–953 (2015)
Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: CVPR, pp. 12697–12705 (2019)
Riegler, G., Osman Ulusoy, A., Geiger, A.: Octnet: learning deep 3D representations at high resolutions. In: CVPR, pp. 3577–3586 (2017)
Maturana, D., Scherer, S.: Voxnet: a 3D convolutional neural network for real-time object recognition. In: IROS, pp. 922–928 (2015)
Jiang, L., Zhao, H., Liu, S., Shen, X., Fu, C.W., Jia, J.: Hierarchical point-edge interaction network for point cloud semantic segmentation. In: ICCV, pp. 10433–10441 (2019)
Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on x-transformed points. NeurIPS 31, 820–830 (2018)
Xu, Y., Fan, T., Xu, M., Zeng, L., Qiao, Yu.: SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 90–105. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_6
Wang, S., Suo, S., Ma, W.C., Pokrovsky, A., Urtasun, R.: Deep parametric continuous convolutional neural networks. In: CVPR, pp. 2589–2597 (2018)
Wu, W., Qi, Z., Fuxin, L.: PointConv: deep convolutional networks on 3D point clouds. In: CVPR, pp. 9621–9630 (2019)
Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: ICCV, pp. 6411–6420 (2019)
Xu, M., Ding, R., Zhao, H., Qi, X.: PaConv: position adaptive convolution with dynamic kernel assembling on point clouds. In: CVPR, pp. 3173–3182 (2021)
Boulch, A., Puy, G., Marlet, R.: FKAConv: feature-kernel alignment for point cloud convolution. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12622, pp. 381–399. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-69525-5_23
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) 38(5), 1–12 (2019)
Wang, L., Huang, Y., Hou, Y., Zhang, S., Shan, J.: Graph attention convolution for point cloud semantic segmentation. In: CVPR, pp. 10296–10305 (2019)
Xu, Q., Sun, X., Wu, C.Y., Wang, P., Neumann, U.: Grid-GCN for fast and scalable point cloud learning. In: CVPR, pp. 5661–5670 (2020)
Zhao, H., Jiang, L., Fu, C.W., Jia, J.: Pointweb: enhancing local neighborhood features for point cloud processing. In: CVPR, pp. 5565–5573 (2019)
Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 663–678. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_39
Hou, J., Dai, A., Nießner, M.: 3D-sis: 3D semantic instance segmentation of RGB-D scans. In: CVPR, pp. 4421–4430 (2019)
Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)
Yi, L., Zhao, W., Wang, H., Sung, M., Guibas, L.J.: GSPN: generative shape proposal network for 3D instance segmentation in point cloud. In: CVPR, pp. 3947–3956 (2019)
Ren, Z., Sudderth, E.B.: Three-dimensional object detection and layout prediction using clouds of oriented gradients. In: CVPR, pp. 1525–1533 (2016)
Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: CVPR, pp. 770–779 (2019)
Shi, S., et al.: Pv-RCNN: point-voxel feature set abstraction for 3D object detection. In: CVPR, pp. 10529–10538 (2020)
Chen, J., Lei, B., Song, Q., Ying, H., Chen, D.Z., Wu, J.: A hierarchical graph network for 3D object detection on point clouds. In: CVPR, pp. 392–401 (2020)
Duan, Y., Zhu, C., Lan, Y., Yi, R., Liu, X., Xu, K.: Disarm: displacement aware relation module for 3D detection. In: CVPR, pp. 16980–16989 (2022)
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jégou, H.: Training data-efficient image transformers & distillation through attention. In: ICML, pp. 10347–10357. PMLR (2021)
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)
Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR, pp. 6881–6890 (2021)
Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. arXiv preprint arXiv:2105.05633 (2021)
Lai, X., et al.: Stratified transformer for 3D point cloud segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8500–8509 (2022)
Wang, Y., Solomon, J.M.: Deep closest point: learning representations for point cloud registration. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3523–3532 (2019)
Fan, H., Yang, Y., Kankanhalli, M.: Point 4D transformer networks for spatio-temporal modeling in point cloud videos. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14204–14213 (2021)
Qiu, S., Anwar, S., Barnes, N.: Pu-transformer: point cloud upsampling transformer. arXiv preprint arXiv:2111.12242 (2021)
Xu, X., Geng, G., Cao, X., Li, K., Zhou, M.: TDnet: transformer-based network for point cloud denoising. Appl. Opt. 61(6), C80–C88 (2022)
Yu, X., Rao, Y., Wang, Z., Liu, Z., Lu, J., Zhou, J.: Pointr: diverse point cloud completion with geometry-aware transformers. In: ICCV, pp. 12498–12507 (2021)
Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: ICCV (2021)
Ma, X., Qin, C., You, H., Ran, H., Fu, Y.: Rethinking network design and local geometry in point cloud: a simple residual MLP framework. In: ICLR (2021)
Peng, Z., et al.: Conformer: local features coupling global representations for visual recognition. arXiv preprint arXiv:2105.03889 (2021)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700–4708 (2017)
Chen, B., Liu, Y., Zhang, Z., Lu, G., Zhang, D.: Transattunet: multi-level attention-guided u-net with transformer for medical image segmentation. arXiv preprint arXiv:2107.05274 (2021)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https://github.com/open-mmlab/mmdetection3d (2020)
Du, H., Li, L., Liu, B., Vasconcelos, N.: SPOT: selective point cloud voting for better proposal in point cloud object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 230–247. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_14
You, Y., et al.: Canonical voting: towards robust oriented bounding box detection in 3D scenes. In: CVPR, pp. 1193–1202 (2022)
Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: going deeper with nested U-structure for salient object detection. Pattern Recogn. 106, 107404 (2020)
Cai, Y., Wang, Y.: Ma-unet: an improved version of unet based on multi-scale and attention mechanism for medical image segmentation. arXiv preprint arXiv:2012.10952 (2020)
Acknowledgements
This work was supported by the Key-Area Research and Development Program of Guangdong Province (No. 2019B010139004) and the National Natural Science Foundation Youth Fund No. 62007001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, C., Yue, K., Liu, Y. (2023). ReAGFormer: Reaggregation Transformer with Affine Group Features for 3D Object Detection. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13841. Springer, Cham. https://doi.org/10.1007/978-3-031-26319-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-26319-4_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26318-7
Online ISBN: 978-3-031-26319-4
eBook Packages: Computer ScienceComputer Science (R0)