{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:18:42Z","timestamp":1771978722894,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T00:00:00Z","timestamp":1658448000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T00:00:00Z","timestamp":1658448000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00371-022-02607-x","type":"journal-article","created":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T14:04:07Z","timestamp":1658498647000},"page":"4543-4554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Stereo 3D object detection via instance depth prior guidance and adaptive spatial feature aggregation"],"prefix":"10.1007","volume":"39","author":[{"given":"Chaofeng","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guizhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,22]]},"reference":[{"key":"2607_CR1","doi-asserted-by":"crossref","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: enhancing point features with image semantics for 3D object detection, arXiv preprint: http:\/\/arxiv.org\/abs\/2007.08856, (2020)","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"2607_CR2","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3D object detection in point clouds, In: IEEE International Conference on Computer Vision (ICCV), pp. 9276\u20139285 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"2607_CR3","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"2607_CR4","doi-asserted-by":"crossref","unstructured":"Shi, R.R.W., Point-GNN: graph neural network for 3D object detection in a point cloud, In: Proceeding of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1708\u20131716 (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"2607_CR5","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: PV-RCNN: point-voxel feature set abstraction for 3D object detection, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10526\u201310535 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"2607_CR6","doi-asserted-by":"crossref","unstructured":"Sun, J., Chen, L., Xie, Y., Zhang, S., Jiang, Q., Zhou, X., Bao, H.: Disp R-CNN: stereo 3D object detection via shape prior guided instance disparity estimation, In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10545\u201310554 (2020)","DOI":"10.1109\/CVPR42600.2020.01056"},{"key":"2607_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Shen, X., Jia, J.: DSGN: deep stereo geometry network for 3D object detection, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12533\u201312542 (2020)","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"2607_CR8","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, X., Shen, S.: Stereo r-cnn based 3d object detection for autonomous driving, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7636\u20137644 (2019)","DOI":"10.1109\/CVPR.2019.00783"},{"key":"2607_CR9","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, J., Lu, Y.: Triangulation learning network: from monocular to stereo 3D object detection, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7607\u20137615 (2019)","DOI":"10.1109\/CVPR.2019.00780"},{"key":"2607_CR10","doi-asserted-by":"crossref","unstructured":"Pon, A.D., Ku, J., Li, C., Waslander, S.L.: Object-centric stereo matching for 3D object detection, In: Proceeding of the IEEE International Conference on Robotics and Automation (ICRA), pp. 8383\u20138389 (2020)","DOI":"10.1109\/ICRA40945.2020.9196660"},{"key":"2607_CR11","doi-asserted-by":"crossref","unstructured":"Peng, W., Pan, H., Liu, H., Sun, Y.: IDA-3D: instance-depth-aware 3D object detection from stereo vision for autonomous driving, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13012\u201313021 (2020)","DOI":"10.1109\/CVPR42600.2020.01303"},{"key":"2607_CR12","doi-asserted-by":"crossref","unstructured":"X. Ma, Z. Wang, H. Li, P. Zhang, X. Fan, W. Ouyang, Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving, in: IEEE International Conference on Computer Vision (ICCV), pp. 6850\u20136859 (2019)","DOI":"10.1109\/ICCV.2019.00695"},{"key":"2607_CR13","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632\u20135640 (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"2607_CR14","doi-asserted-by":"crossref","unstructured":"Li, B., Ouyang, W., Lu, J., Zeng, X., Wang, X.: GS3D: an efficient 3D object detection framework for autonomous driving, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1019\u20131028 (2019)","DOI":"10.1109\/CVPR.2019.00111"},{"key":"2607_CR15","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3d-rpn: monocular 3d region proposal network for object detection, In: IEEE International Conference on Computer Vision (ICCV), pp. 9287\u20139296 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"2607_CR16","unstructured":"Xiaozhi, C., Kaustav, K., Ziyu, Z., Huimin, M., Raquel, U.: Monocular 3D object detection for autonomous driving, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2147\u20132156 (2016)"},{"key":"2607_CR17","doi-asserted-by":"crossref","unstructured":"Ku, J., Pon, A.D., Waslander, S.L.: Monocular 3D object detection leveraging accurate proposals and shape reconstruction, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11867\u201311876 (2019)","DOI":"10.1109\/CVPR.2019.01214"},{"key":"2607_CR18","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, J., Lu, Y.: MonoGRNet: a geometric reasoning network for monocular 3D object localization, In: AAAI Conference on Artificial Intelligence (AAAI), pp. 8851\u20138858 (2019)","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"2607_CR19","doi-asserted-by":"crossref","unstructured":"Ma, X., Liu, S., Xia, Z., Zhang, H., Zeng, X., Ouyang, W.: Rethinking pseudo-LiDAR representation, arXiv preprint: http:\/\/arxiv.org\/abs\/2008.04582, (2020)","DOI":"10.1007\/978-3-030-58601-0_19"},{"key":"2607_CR20","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3d object detection from monocular images, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2345\u20132353 (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"2607_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.-L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: bridging the gap in 3d object detection for autonomous driving, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8445\u20138453 (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"2607_CR22","unstructured":"You, Y., Wang, Y., Chao, W.L., Garg, D., Pleiss, G., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-LiDAR++: accurate depth for 3D object detection in autonomous driving, arXiv preprint: http:\/\/arxiv.org\/abs\/1906.06310, (2019)"},{"key":"2607_CR23","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2607_CR24","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation, In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 5750\u20135757 (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"2607_CR25","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points, arXivpreprint http:\/\/arxiv.org\/abs\/1904.07850 (2019)"},{"key":"2607_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: SMOKE: single-stage monocular 3D Object Detection via Keypoint Estimation, In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 4289\u20134298 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"2607_CR27","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3D detection from object keypoints for autonomous driving, arXivpreprint: http:\/\/arxiv.org\/abs\/2001.03343 (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"2607_CR28","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., Li, M.: MonoPair: monocular 3D object detection using pairwise spatial relationships, In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12090\u201312099 (2020)","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"2607_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, H., Yang, D., Yu, J.: 3D target detection using dual domain attention and SIFT operator in indoor scenes, The Visual Computer, pp. 1\u201310 (2021)","DOI":"10.1007\/s00371-021-02217-z"},{"key":"2607_CR30","doi-asserted-by":"crossref","unstructured":"Chang, J., Chen, Y.: Pyramid stereo matching network, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5410\u20135418 (2018)","DOI":"10.1109\/CVPR.2018.00567"},{"key":"2607_CR31","doi-asserted-by":"crossref","unstructured":"Li, X., Fan, Y., Lv, G., Ma, H.: Area-based correlation and non-local attention network for stereo matching, The Visual Computer, pp. 1\u201315 (2021)","DOI":"10.1007\/s00371-021-02228-w"},{"key":"2607_CR32","doi-asserted-by":"crossref","unstructured":"Qian, R., Garg, D., Wang, Y., You, Y., Belongie, S., Hariharan, B., Campbell, M., Weinberger, K.Q., Chao, W.L.: End-to-end pseudo-LiDAR for image-based 3D object detection, In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5880\u20135889 (2020)","DOI":"10.1109\/CVPR42600.2020.00592"},{"key":"2607_CR33","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints, In: European Conference on Computer Vision (ECCV), pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2607_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection, IEEE Transactions on Pattern Analysis & Machine Intelligence (TPAMI), pp. 2999\u20133007 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2607_CR35","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2607_CR36","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation, In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2403\u20132412 (2018)","DOI":"10.1109\/CVPR.2018.00255"},{"key":"2607_CR37","doi-asserted-by":"crossref","unstructured":"Ku, J., Harakeh, A., Waslander, S.L.: In defense of classical image processing: fast depth completion on the CPU, In: Proceedings of 2018 15th Conference on Computer and Robot Vision (CRV), pp. 16\u201322 (2018)","DOI":"10.1109\/CRV.2018.00013"},{"key":"2607_CR38","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, W., Ye, X., Tan, X., Yang, W., Wen, S., Ding, E., Meng, A., Huang, L.: ZoomNet: part-aware adaptive zooming neural network for 3D object detection, In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 12557\u201312564 (2020)","DOI":"10.1609\/aaai.v34i07.6945"},{"key":"2607_CR39","doi-asserted-by":"crossref","unstructured":"Li, C., Ku, J., Waslander, S.L.: Confidence guided stereo 3D object detection with split depth estimation, In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 5776\u20135783 (2020)","DOI":"10.1109\/IROS45743.2020.9341188"},{"key":"2607_CR40","unstructured":"Garg, D., Wang, Y., Hariharan, B., Campbell, M., Weinberger, K.Q., Chao, W.-L.: Wasserstein distances for stereo disparity estimation, In: Advances in Neural Information Processing Systems (NeurIPS), (2020)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02607-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02607-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02607-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:01:05Z","timestamp":1727632865000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02607-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,22]]},"references-count":40,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["2607"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02607-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,22]]},"assertion":[{"value":"22 June 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}