{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:10:30Z","timestamp":1774602630135,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11263-026-02735-0","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T07:41:43Z","timestamp":1770104503000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PARTNER: Level Up the Polar Representation for 3D Object Detection"],"prefix":"10.1007","volume":"134","author":[{"given":"Ming","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-5420","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"2735_CR1","doi-asserted-by":"crossref","unstructured":"Bai, X., Hu, Z., Zhu, X., Huang, Q., Chen, Y., Fu, H., & Tai, C. -L. (2022). Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. In: CVPR","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"2735_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). nuscenes: A multimodal dataset for autonomous driving. In: CVPR","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2735_CR3","doi-asserted-by":"crossref","unstructured":"Chai, Y., Sun, P., Ngiam, J., Wang, W., Caine, B., Vasudevan, V., Zhang, X., & Anguelov, D. (2021). To the point: Efficient 3d object detection in the range image with graph convolution kernels. In: CVPR","DOI":"10.1109\/CVPR46437.2021.01574"},{"key":"2735_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F., Zhou, B., & Zhao, H. (2022). Autoalign: Pixel-instance feature aggregation for multi-modal 3d object detection. arXiv preprint","DOI":"10.24963\/ijcai.2022\/116"},{"key":"2735_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., & Xia, T. (2017). Multi-view 3d object detection network for autonomous driving. In: CVPR","DOI":"10.1109\/CVPR.2017.691"},{"key":"2735_CR6","unstructured":"Chen, Q., Vora, S., & Beijbom, O. (2021). Polarstream: Streaming object detection and segmentation with polar pillars. NIPS"},{"key":"2735_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, T., Wang, Y., Wang, Y., & Zhao, H. (2023). Futr3d: A unified sensor fusion framework for 3d detection. In: CVPR","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"2735_CR8","doi-asserted-by":"crossref","unstructured":"Chenhang\u00a0He, S. L. Ruihuang\u00a0Li, & Zhang, L. (2022). Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. In: CVPR","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"2735_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint"},{"key":"2735_CR10","doi-asserted-by":"crossref","unstructured":"Duan, Z., Dang, C., Hu, X., An, P., Ding, J., Zhan, J., Xu, Y., & Ma, J. (2025). Sdgocc: Semantic and depth-guided bird\u2019s-eye view transformation for 3d multimodal occupancy prediction. In: CVPR","DOI":"10.1109\/CVPR52734.2025.00633"},{"key":"2735_CR11","doi-asserted-by":"crossref","unstructured":"Fan, L., Pang, Z., Zhang, T., Wang, Y.-X., Zhao, H., Wang, F., Wang, N., & Zhang, Z. (2022). Embracing single stride 3d object detector with sparse transformer. In: CVPR","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"2735_CR12","doi-asserted-by":"crossref","unstructured":"Fan, L., Xiong, X., Wang, F., Wang, N., & Zhang, Z. (2021). Rangedet: In defense of range view for lidar-based 3d object detection. In: ICCV","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"2735_CR13","unstructured":"Frossard, D., Da\u00a0Suo, S., Casas, S., Tu, J., & Urtasun, R. (2021). Strobe: Streaming object detection from lidar packets. In: CoRL. PMLR"},{"key":"2735_CR14","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K., Tao, D. (2018). Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00214"},{"key":"2735_CR15","doi-asserted-by":"crossref","unstructured":"Han, W., Zhang, Z., Caine, B., Yang, B., Sprunk, C., Alsharif, O., Ngiam, J., Vasudevan, V., Shlens, J., & Chen, Z. (2020). Streaming object detection for 3-d point clouds. In: ECCV . Springer","DOI":"10.1007\/978-3-030-58523-5_25"},{"key":"2735_CR16","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., & Salimans, T. (2019). Axial attention in multidimensional transformers. arXiv preprint"},{"key":"2735_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, L., Miao, Z., Zhu, X., Gao, J., Hu, W., & Jiang, Y. -G. (2023). Polarformer: Multi-camera 3d object detection with polar transformer. In: AAAI","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"2735_CR18","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., & Beijbom, O. (2019). Pointpillars: Fast encoders for object detection from point clouds. In: CVPR","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2735_CR19","doi-asserted-by":"crossref","unstructured":"Li, S., Li, P., Lian, Q., Yun, P., & Chen, X. (2025). Learning better representations for crowded pedestrians in offboard lidar-camera 3d tracking-by-detection. arXiv preprint","DOI":"10.1109\/ICRA55743.2025.11128508"},{"key":"2735_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Qiao, Y., & Dai, J. (2022). Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"2735_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, A.W., Meng, T., Caine, B., Ngiam, J., Peng, D., Shen, J., Lu, Y., Zhou, D., Le, Q.V., et al. (2022). Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection. In: CVPR","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"2735_CR22","doi-asserted-by":"crossref","unstructured":"Liang, T., Xie, H., Yu, K., Xia, Z., Lin, Z., Wang, Y., Tang, T., Wang, B., & Tang, Z. (2022). Bevfusion: A simple and robust lidar-camera fusion framework. NIPS","DOI":"10.52202\/068431-0757"},{"key":"2735_CR23","unstructured":"Liang, Z., Zhang, M., Zhang, Z., Zhao, X., & Pu, S. (2020). Rangercnn: Towards fast and accurate 3d object detection with range image representation. arXiv preprint"},{"key":"2735_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017). Focal loss for dense object detection. In: ICCV","DOI":"10.1109\/ICCV.2017.324"},{"key":"2735_CR25","doi-asserted-by":"crossref","unstructured":"Lin, Z., Liu, Z., Xia, Z., Wang, X., Wang, Y., Qi, S., Dong, Y., Dong, N., Zhang, L., & Zhu, C. (2024). Rcbevdet: Radar-camera fusion in bird\u2019s eye view for 3d object detection. In: CVPR","DOI":"10.1109\/CVPR52733.2024.01414"},{"key":"2735_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2735_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2735_CR28","doi-asserted-by":"crossref","unstructured":"Mao, J., Niu, M., Bai, H., Liang, X., Xu, H., & Xu, C. (2021). Pyramid r-cnn: Towards better performance and adaptability for 3d object detection. In: ICCV","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"2735_CR29","unstructured":"Mao, J., Niu, M., Jiang, C., Liang, H., Chen, J., Liang, X., Li, Y., Ye, C., Zhang, W., Li, Z., et al. (2021). One million scenes for autonomous driving: Once dataset. arXiv preprint"},{"key":"2735_CR30","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., & Xu, C. (2021). Voxel transformer for 3d object detection. In: ICCV","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"2735_CR31","doi-asserted-by":"crossref","unstructured":"Nabati, R., & Qi, H. (2021). Centerfusion: Center-based radar and camera fusion for 3d object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"2735_CR32","doi-asserted-by":"crossref","unstructured":"Nie, M., Xue, Y., Wang, C., Ye, C., Xu, H., Zhu, X., Huang, Q., Mi, M.B., Wang, X., & Zhang, L. (2023). Partner: Level up the polar representation for lidar 3d object detection. In: ICCV","DOI":"10.1109\/ICCV51070.2023.00352"},{"key":"2735_CR33","doi-asserted-by":"crossref","unstructured":"Philion, J., & Fidler, S. (2020). Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In: ECCV","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"2735_CR34","unstructured":"Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation. In: CVPR"},{"key":"2735_CR35","unstructured":"Qi, C.R., Yi, L., Su, H., & Guibas, L. J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. NIPS"},{"key":"2735_CR36","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., & Waslander, S. L. (2021). Categorical depth distribution network for monocular 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"2735_CR37","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., & Li, H. (2020). Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: CVPR","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"2735_CR38","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., & Li, H. (2019). Pointrcnn: 3d object proposal generation and detection from point cloud. In: CVPR","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2735_CR39","unstructured":"Su, Y. -C., & Grauman, K. (2017). Learning spherical convolution for fast features from 360 imagery."},{"key":"2735_CR40","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et al. (2020). Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"2735_CR41","doi-asserted-by":"crossref","unstructured":"Sun, P., Tan, M., Wang, W., Liu, C., Xia, F., Leng, Z., & Anguelov, D. (2022). Swformer: Sparse window transformer for 3d object detection in point clouds. In: ECCV","DOI":"10.1007\/978-3-031-20080-9_25"},{"key":"2735_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., & Jia, K. (2019). Frustum convnet: Sliding frustums to aggregate local point-wise features for amodal 3d object detection. In: IROS","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"2735_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fathi, A., Kundu, A., Ross, D. A., Pantofaru, C., Funkhouser, T. A., & Solomon, J. M. (2020). Pillar-based object detection for autonomous driving. In: ECCV","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"2735_CR44","unstructured":"Xie, E., Yu, Z., Zhou, D., Philion, J., Anandkumar, A., Fidler, S., Luo, P., & Alvarez, J. M. (2022). $$\\text{M}^{2}$$bev: Multi-camera joint 3d detection and segmentation with unified birds-eye view representation. arXiv preprint"},{"key":"2735_CR45","doi-asserted-by":"crossref","unstructured":"Xu, S., Zhou, D., Fang, J., Yin, J., Bin, Z., & Zhang, L. (2021). Fusionpainting: Multimodal fusion with adaptive attention for 3d object detection. In: ITSC","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"2735_CR46","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., & Li, B. (2018). Second: Sparsely embedded convolutional detection. Sensors","DOI":"10.3390\/s18103337"},{"key":"2735_CR47","doi-asserted-by":"crossref","unstructured":"Yang, H., Bai, X., Zhu, X., & Ma, Y. (2023). One training for multiple deployments: Polar-based adaptive bev perception for autonomous driving. In: ICRA","DOI":"10.1109\/ICRA48891.2023.10161552"},{"key":"2735_CR48","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., & Jia, J. (2020). 3dssd: Point-based 3d single stage object detector. In: CVPR","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"2735_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., & Jia, J. (2019). Std: Sparse-to-dense 3d object detector for point cloud. In: ICCV","DOI":"10.1109\/ICCV.2019.00204"},{"key":"2735_CR50","doi-asserted-by":"crossref","unstructured":"Yin, J., Shen, J., Chen, R., Li, W., Yang, R., Frossard, P., & Wang, W. (2024). Is-fusion: Instance-scene collaborative fusion for multimodal 3d object detection. In: CVPR","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"2735_CR51","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., & Kr\u00e4henb\u00fchl, P. (2020). Center-based 3d object detection and tracking. arXiv preprint","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"2735_CR52","unstructured":"Yin, T., Zhou, X., & Kr\u00e4henb\u00fchl, P. (2021). Multimodal virtual point 3d detection. NIPS"},{"key":"2735_CR53","doi-asserted-by":"crossref","unstructured":"Yogamani, S., Hughes, C., Horgan, J., Sistu, G., Varley, P., O\u2019Dea, D., Uric\u00e1r, M., Milz, S., Simon, M., Amende, K., et al. (2019). Woodscape: A multi-task, multi-camera fisheye dataset for autonomous driving. In: ICCV","DOI":"10.1109\/ICCV.2019.00940"},{"key":"2735_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, Z., David, P., Yue, X., Xi, Z., Gong, B., & Foroosh, H. (2020). Polarnet: An improved grid representation for online lidar point clouds semantic segmentation. In: CVPR","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"2735_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., & Tuzel, O. (2018). Voxelnet: End-to-end learning for point cloud based 3d object detection. In: CVPR","DOI":"10.1109\/CVPR.2018.00472"},{"key":"2735_CR56","unstructured":"Zhou, Y., Sun, P., Zhang, Y., Anguelov, D., Gao, J., Ouyang, T., Guo, J., Ngiam, J., & Vasudevan, V. (2020). End-to-end multi-view fusion for 3d object detection in lidar point clouds. In: CoRL. PMLR"},{"key":"2735_CR57","unstructured":"Zhou, D., Yu, Z., Xie, E., Xiao, C., Anandkumar, A., Feng, J., & Alvarez, J. M. (2022). Understanding the robustness in vision transformers. In: ICML. PMLR, ???"},{"key":"2735_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhao, X., Wang, Y., Wang, P., & Foroosh, H. (2022). Centerformer: Center-based transformer for 3d object detection. In: ECCV","DOI":"10.1007\/978-3-031-19839-7_29"},{"key":"2735_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, B., Wang, Z., Shi, S., Xu, H., Hong, L., & Li, H. (2023). Conquer: Query contrast voxel-detr for 3d object detection. In: CVPR","DOI":"10.1109\/CVPR52729.2023.00897"},{"key":"2735_CR60","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., & Lin, D. (2021). Cylindrical and asymmetrical 3d convolution networks for lidar segmentation. In: CVPR","DOI":"10.1109\/CVPR46437.2021.00981"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02735-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02735-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02735-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:33:02Z","timestamp":1774600382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02735-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["2735"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02735-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"assertion":[{"value":"22 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"98"}}