Abstract
Point cloud datasets suffer from a large domain discrepancy due to variations in data acquisition procedures, sensor perspectives, and realistic noise. To address this issue, domain adaptation technologies have emerged to improve scalability and generalization for point cloud models. We propose a novel method named GeoCo-TSDA (Geometry-Correlation Prediction and Target-Specific Domain Adaptation) which boosts the performance of domain adaptation with a geometry-correlation prediction task and a target-specific self-training strategy. We design a self-supervised task that predicts the geometry correlation, which is obtained by the covariance of the local point clusters and is related to a variety of geometric properties, enabling the model to learn more complete and robust features. Moreover, existing domain adaptation methods commonly focus on aligning feature space among domains. However, owing to the internal distribution gap among domains, merely aligning features at the domain level falls short of achieving optimal performance for the target domain. We tackle this problem by adding a target domain specific training procedure that focuses on further adapting the model to fit the internal distribution of the target domain. For the rationality of our method, we provide theoretical and empirical analysis. For the effectiveness of our method, we conduct experiments on commonly used benchmark PointDA-10 and GraspNetPC-10, and on both datasets our model achieves SOTA performance among point cloud domain adaptation methods and considerable elevation compared to the baseline model.
Junqiao Li and Leyan Zhu—The first two authors contribute equally to this work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achituve, I., Maron, H., Chechik, G.: Self-supervised learning for domain adaptation on point clouds. In: WACV, pp. 123–133 (2021)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. NeurIPS 19 (2006)
Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al.: Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)
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)
Fan, H., Chang, X., Zhang, W., Cheng, Y., Sun, Y., Kankanhalli, M.: Self-supervised global-local structure modeling for point cloud domain adaptation with reliable voted pseudo labels. In: CVPR, pp. 6377–6386 (2022)
Fang, H.S., Wang, C., Gou, M., Lu, C.: Graspnet-1billion: a large-scale benchmark for general object grasping. In: CVPR, pp. 11444–11453 (2020)
Hou, J., Graham, B., Nießner, M., Xie, S.: Exploring data-efficient 3d scene understanding with contrastive scene contexts. In: CVPR, pp. 15587–15597 (2021)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Li, Y., Ma, L., Zhong, Z., Liu, F., Chapman, M.A., Cao, D., Li, J.: Deep learning for lidar point clouds in autonomous driving: a review. TNNLS 32(8), 3412–3432 (2020)
Liang, H., Fan, H., Fan, Z., Wang, Y., Chen, T., Cheng, Y., Wang, Z.: Point cloud domain adaptation via masked local 3d structure prediction. In: ECCV, pp. 156–172. Springer (2022)
Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: CVPR, pp. 8895–8904 (2019)
Maturana, D., Scherer, S.: Voxnet: a 3d convolutional neural network for real-time object recognition. In: IROS, pp. 922–928. IEEE (2015)
Pan, F., Shin, I., Rameau, F., Lee, S., Kweon, I.S.: Unsupervised intra-domain adaptation for semantic segmentation through self-supervision. In: CVPR, pp. 3764–3773 (2020)
Park, J., Seo, H., Yang, E.: Pc-adapter: Topology-aware adapter for efficient domain adaption on point clouds with rectified pseudo-label. In: ICCV, pp. 11530–11540 (2023)
Poursaeed, O., Jiang, T., Qiao, H., Xu, N., Kim, V.G.: Self-supervised learning of point clouds via orientation estimation. In: 3DV, pp. 1018–1028. IEEE (2020)
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., Su, H., Nießner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view cnns for object classification on 3d data. In: CVPR, pp. 5648–5656 (2016)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. NeurIPS 30 (2017)
Qin, C., You, H., Wang, L., Kuo, C.C.J., Fu, Y.: Pointdan: a multi-scale 3d domain adaption network for point cloud representation. NeurIPS 32 (2019)
Sauder, J., Sievers, B.: Self-supervised deep learning on point clouds by reconstructing space. NeurIPS 32 (2019)
Shen, Y., Yang, Y., Yan, M., Wang, H., Zheng, Y., Guibas, L.J.: Domain adaptation on point clouds via geometry-aware implicits. In: CVPR, pp. 7223–7232 (2022)
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. In: ICCV, pp. 945–953 (2015)
Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In: CVPR, pp. 2517–2526 (2019)
Wang, H., Liu, Q., Yue, X., Lasenby, J., Kusner, M.J.: Unsupervised point cloud pre-training via occlusion completion. In: ICCV, pp. 9782–9792 (2021)
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph cnn for learning on point clouds. TOG 38(5), 1–12 (2019)
Wu, W., Qi, Z., Fuxin, L.: Pointconv: deep convolutional networks on 3d point clouds. In: CVPR, pp. 9621–9630 (2019)
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3d shapenets: a deep representation for volumetric shapes. In: CVPR, pp. 1912–1920 (2015)
Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: Pointcontrast: unsupervised pre-training for 3d point cloud understanding. In: ECCV, pp. 574–591. Springer (2020)
Zhang, Y., Lin, J., He, C., Chen, Y., Jia, K., Zhang, L.: Masked surfel prediction for self-supervised point cloud learning. arXiv preprint arXiv:2207.03111 (2022)
Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3d features on any point-cloud. In: ICCV, pp. 10252–10263 (2021)
Zou, L., Tang, H., Chen, K., Jia, K.: Geometry-aware self-training for unsupervised domain adaptation on object point clouds. In: ICCV, pp. 6403–6412 (2021)
Acknowledgement
This work was supported by the National Key Research and Development Program of China (2023YFC3306401), National Natural Science Foundation of China (62032016, 62141604), Beijing Nova Program (20220484106, 20230484451).
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
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, J., Zhu, L., Wang, T., Xie, Y., Shi, J., Snoussi, H. (2025). Target-Specific Domain Adaptation via Geometry-Correlation Prediction for Point Cloud. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15034. Springer, Singapore. https://doi.org/10.1007/978-981-97-8505-6_4
Download citation
DOI: https://doi.org/10.1007/978-981-97-8505-6_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-8504-9
Online ISBN: 978-981-97-8505-6
eBook Packages: Computer ScienceComputer Science (R0)