{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:38:26Z","timestamp":1764995906112,"version":"3.46.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2024YFC3015302"],"award-info":[{"award-number":["2024YFC3015302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372377"],"award-info":[{"award-number":["62372377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M761014"],"award-info":[{"award-number":["2024M761014"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11263-025-02575-4","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T10:57:34Z","timestamp":1758279454000},"page":"8589-8616","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhance Image-to-Point-Cloud Registration with Beltrami Flow"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3645-8465","authenticated-orcid":false,"given":"Pei","family":"An","sequence":"first","affiliation":[]},{"given":"You","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jiaqi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Muyao","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Qiong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Liangliang","family":"Nan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"2575_CR1","doi-asserted-by":"publisher","first-page":"18261","DOI":"10.1364\/OE.394331","volume":"28","author":"P An","year":"2020","unstructured":"An, P., Gao, Y., Ma, T., Yu, K., Fang, B., Zhang, J., & Ma, J. (2020). Lidar-camera system extrinsic calibration by establishing virtual point correspondences from pseudo calibration objects. Opt. Express, 28, 18261\u201318282.","journal-title":"Opt. Express"},{"key":"2575_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103295","volume":"214","author":"P An","year":"2022","unstructured":"An, P., Liang, J., Yu, K., Fang, B., & Ma, J. (2022). Deep structural information fusion for 3d object detection on lidar-camera system. Comput. Vis. Image Underst., 214, Article 103295.","journal-title":"Comput. Vis. Image Underst."},{"key":"2575_CR3","doi-asserted-by":"crossref","unstructured":"An P, Ding J, Quan S, Yang J, Yang Y, Liu Q, & Ma J (2024a) Survey of extrinsic calibration on lidar-camera system for intelligent vehicle: Challenges, approaches, and trends. IEEE Trans Intell Transp Syst Early Access(1):1\u201325","DOI":"10.1109\/TITS.2024.3419758"},{"issue":"1","key":"2575_CR4","first-page":"1","volume":"1","author":"P An","year":"2024","unstructured":"An, P., Hu, X., Ding, J., Zhang, J., Ma, J., Yang, Y., & Liu, Q. (2024). Ol-reg: Registration of image and sparse lidar point cloud with object-level dense correspondences. IEEE Trans. Circuits Syst. Video Technol., 1(1), 1\u201315.","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2575_CR5","doi-asserted-by":"crossref","unstructured":"Bae G, & Davison AJ (2024) Rethinking inductive biases for surface normal estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u201310","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"2575_CR6","doi-asserted-by":"crossref","unstructured":"Bastico M, Decenci\u00e8re E, Cort\u00e9 L, Tillier Y, & Ryckelynck D (2024) Coupled laplacian eigenmaps for locally-aware 3d rigid point cloud matching. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3447\u20133458","DOI":"10.1109\/CVPR52733.2024.00331"},{"key":"2575_CR7","doi-asserted-by":"crossref","unstructured":"Brachmann E, Cavallari T, & Prisacariu VA (2023) Accelerated coordinate encoding: Learning to relocalize in minutes using RGB and poses. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5044\u20135053","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"2575_CR8","doi-asserted-by":"crossref","unstructured":"Campbell D, Liu L, & Gould S (2020) Solving the blind perspective-n-point problem end-to-end with robust differentiable geometric optimization. In: Proceedings of European Conference on Computer Vision, pp 244\u2013261","DOI":"10.1007\/978-3-030-58536-5_15"},{"key":"2575_CR9","unstructured":"Chamberlain B, Rowbottom J, Eynard D, Giovanni FD, Dong X, & Bronstein MM (2021a) Beltrami flow and neural diffusion on graphs. In: Proceedings of Advances in Neural Information Processing Systems, pp 1594\u20131609"},{"key":"2575_CR10","unstructured":"Chamberlain B, Rowbottom J, Gorinova MI, Bronstein MM, Webb S, & Rossi E (2021b) GRAND: graph neural diffusion. In: Proceedings of the 38th International Conference on Machine Learning, vol 139, pp 1407\u20131418"},{"key":"2575_CR11","doi-asserted-by":"crossref","unstructured":"Chang M, Mangelson JG, Kaess M, & Lucey S (2021) Hypermap: Compressed 3d map for monocular camera registration. In: Proceedings of IEEE International Conference on Robotics and Automation, pp 11739\u201311745","DOI":"10.1109\/ICRA48506.2021.9561864"},{"key":"2575_CR12","doi-asserted-by":"crossref","unstructured":"Chen H, Wang P, Wang F, Tian W, Xiong L, & Li H (2022) Epro-pnp: Generalized end-to-end probabilistic perspective-n-points for monocular object pose estimation. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2771\u20132780","DOI":"10.1109\/CVPR52688.2022.00280"},{"key":"2575_CR13","first-page":"1","volume":"20","author":"Y Cheng","year":"2023","unstructured":"Cheng, Y., Huang, Z., Quan, S., Cao, X., Zhang, S., & Yang, J. (2023). Sampling locally, hypothesis globally: accurate 3d point cloud registration with a ransac variant. Visual Intelligence, 20, 1\u201315.","journal-title":"Visual Intelligence"},{"key":"2575_CR14","doi-asserted-by":"crossref","unstructured":"Cheng Z, Deng J, Li X, Yin B, & Zhang T (2025) Bridge 2d-3d: Uncertainty-aware hierarchical registration network with domain alignment. In: Proceedings of AAAI Conference on Artificial Intelligence, pp 2491\u20132499","DOI":"10.1609\/aaai.v39i3.32251"},{"key":"2575_CR15","doi-asserted-by":"crossref","unstructured":"Choy CB, Park J, & Koltun V (2019) Fully convolutional geometric features. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp 8957\u20138965","DOI":"10.1109\/ICCV.2019.00905"},{"key":"2575_CR16","doi-asserted-by":"crossref","unstructured":"Dai A, Chang AX, Savva M, Halber M, Funkhouser TA, & Nie\u00dfner M (2017) Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 2432\u20132443","DOI":"10.1109\/CVPR.2017.261"},{"issue":"3","key":"2575_CR17","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1023\/B:VISI.0000025800.10423.1f","volume":"59","author":"P David","year":"2004","unstructured":"David, P., DeMenthon, D., Duraiswami, R., & Samet, H. (2004). Softposit: Simultaneous pose and correspondence determination. Int. J. Comput. Vis., 59(3), 259\u2013284.","journal-title":"Int. J. Comput. Vis."},{"key":"2575_CR18","doi-asserted-by":"crossref","unstructured":"Dusmanu M, Rocco I, Pajdla T, Pollefeys M, Sivic J, Torii A, & Sattler T (2019) D2-net: A trainable CNN for joint description and detection of local features. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 8092\u20138101","DOI":"10.1109\/CVPR.2019.00828"},{"key":"2575_CR19","doi-asserted-by":"crossref","unstructured":"Feng M, Hu S, Ang MH, & Lee GH (2019) 2D3D-Matchnet: Learning to match keypoints across 2D image and 3D point cloud. In: Proceedings of IEEE International Conference on Robotics and Automation, pp 4790\u20134796","DOI":"10.1109\/ICRA.2019.8794415"},{"key":"2575_CR20","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, & Urtasun R (2012) Are we ready for autonomous driving? the KITTI vision benchmark suite. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2575_CR21","doi-asserted-by":"crossref","unstructured":"Glocker B, Izadi S, Shotton J, & Criminisi A (2013) Real-time RGB-D camera relocalization. In: Proceedings of IEEE International Symposium on Mixed and Augmented Reality, pp 173\u2013179","DOI":"10.1109\/ISMAR.2013.6671777"},{"key":"2575_CR22","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, & Sun J (2016) Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2575_CR23","doi-asserted-by":"crossref","unstructured":"Huang S, Gojcic Z, Usvyatsov M, Wieser A, & Schindler K (2021) Predator: Registration of 3d point clouds with low overlap. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 4267\u20134276","DOI":"10.1109\/CVPR46437.2021.00425"},{"issue":"11","key":"2575_CR24","doi-asserted-by":"publisher","first-page":"10264","DOI":"10.1109\/LRA.2024.3466068","volume":"9","author":"S Kang","year":"2024","unstructured":"Kang, S., Liao, Y., Li, J., Liang, F., Li, Y., Zou, X., Li, F., Chen, X., Dong, Z., & Yang, B. (2024). Cofii2p: Coarse-to-fine correspondences-based image to point cloud registration. IEEE Robotics Autom Lett, 9(11), 10264\u201310271.","journal-title":"IEEE Robotics Autom Lett"},{"key":"2575_CR25","doi-asserted-by":"crossref","unstructured":"Kim M, Koo J, & Kim G (2023) Ep2p-loc: End-to-end 3d point to 2d pixel localization for large-scale visual localization. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp 21470\u201321480","DOI":"10.1109\/ICCV51070.2023.01968"},{"key":"2575_CR26","doi-asserted-by":"crossref","unstructured":"Lai K, Bo L, & Fox D (2014) Unsupervised feature learning for 3d scene labeling. In: Proceedings of IEEE International Conference on Robotics and Automation, pp 3050\u20133057","DOI":"10.1109\/ICRA.2014.6907298"},{"issue":"2","key":"2575_CR27","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11263-008-0152-6","volume":"81","author":"V Lepetit","year":"2009","unstructured":"Lepetit, V., Moreno-Noguer, F., & Fua, P. (2009). EPnP: An accurate O(n) solution to the pnp problem. Int. J. Comput. Vis., 81(2), 155\u2013166.","journal-title":"Int. J. Comput. Vis."},{"key":"2575_CR28","doi-asserted-by":"crossref","unstructured":"Li J, & Lee GH (2021) DeepI2P: Image-to-point cloud registration via deep classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 15960\u201315969","DOI":"10.1109\/CVPR46437.2021.01570"},{"key":"2575_CR29","doi-asserted-by":"crossref","unstructured":"Li M, Qin Z, Gao Z, Yi R, Zhu C, Guo Y, & Xu K (2023) 2D3D-MATR: 2D-3D matching transformer for detection-free registration between images and point clouds. In: Proceedings of IEEE Conference on Computer Vision, pp 1\u201310","DOI":"10.1109\/ICCV51070.2023.01299"},{"issue":"4","key":"2575_CR30","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1007\/s11263-023-01909-4","volume":"132","author":"S Liu","year":"2024","unstructured":"Liu, S., Suganuma, M., & Okatani, T. (2024). Symmetry-aware neural architecture for embodied visual navigation. Int. J. Comput. Vis., 132(4), 1091\u20131107.","journal-title":"Int. J. Comput. Vis."},{"key":"2575_CR31","doi-asserted-by":"crossref","unstructured":"Liu Z, Tang H, Zhu S, & Han S (2021) SemAlign: Annotation-free camera-lidar calibration with semantic alignment loss. In: Proceedings of IEEE International Conference on Intelligent Robots and Systems, pp 8845\u20138851","DOI":"10.1109\/IROS51168.2021.9635964"},{"issue":"2","key":"2575_CR32","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2), 91\u2013110.","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"2575_CR33","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1109\/TMECH.2023.3241398","volume":"28","author":"J Lv","year":"2023","unstructured":"Lv, J., Lang, X., Xu, J., Wang, M., Liu, Y., & Zuo, X. (2023). Continuous-time fixed-lag smoothing for lidar-inertial-camera slam. IEEE\/ASME Trans. Mechatron., 28(4), 2259\u20132270.","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"2575_CR34","doi-asserted-by":"crossref","unstructured":"Matsumoto Y, Nakano G, & Ogura K (2024) Indoor visual localization using point and line correspondences in dense colored point cloud. In: Proceedings of IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 3604\u20133613","DOI":"10.1109\/WACV57701.2024.00358"},{"key":"2575_CR35","unstructured":"Miao J, Jiang K, Wen T, Wang Y, Jia P, Zhao X, Xiao Z, Huang J, Zhong Z, & Yang D (2023) A survey on monocular re-localization: From the perspective of scene map representation. CoRR abs\/2311.15643"},{"key":"2575_CR36","first-page":"405","volume":"5303","author":"F Moreno-Noguer","year":"2008","unstructured":"Moreno-Noguer, F., Lepetit, V., & Fua, P. (2008). Pose priors for simultaneously solving alignment and correspondence. Proceedings of European Conference on Computer Vision, 5303, 405\u2013418.","journal-title":"Proceedings of European Conference on Computer Vision"},{"key":"2575_CR37","doi-asserted-by":"crossref","unstructured":"Pham Q, Uy MA, Hua B, Nguyen DT, Roig G, & Yeung S (2020) LCD: learned cross-domain descriptors for 2d-3d matching. In: Proceedings of AAAI Conference on Artificial Intelligence, pp 11856\u201311864","DOI":"10.1609\/aaai.v34i07.6859"},{"key":"2575_CR38","first-page":"5236","volume":"195","author":"L Pillaud-Vivien","year":"2023","unstructured":"Pillaud-Vivien, L., & Bach, F. R. (2023). Kernelized diffusion maps. Proceedings of The Thirty Sixth Annual Conference on Learning Theory, 195, 5236\u20135259.","journal-title":"Proceedings of The Thirty Sixth Annual Conference on Learning Theory"},{"key":"2575_CR39","doi-asserted-by":"crossref","unstructured":"Qin Z, Yu H, Wang C, Guo Y, Peng Y, & Xu K (2022) Geometric transformer for fast and robust point cloud registration. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11133\u201311142","DOI":"10.1109\/CVPR52688.2022.01086"},{"issue":"3","key":"2575_CR40","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.1109\/TCSVT.2022.3208859","volume":"33","author":"S Ren","year":"2023","unstructured":"Ren, S., Zeng, Y., Hou, J., & Chen, X. (2023). CorrI2P: Deep image-to-point cloud registration via dense correspondence. IEEE Trans. Circuits Syst. Video Technol., 33(3), 1198\u20131208.","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2575_CR41","doi-asserted-by":"crossref","unstructured":"Sarlin P, DeTone D, Malisiewicz T, & Rabinovich A (2020) Superglue: Learning feature matching with graph neural networks. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4937\u20134946","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"2575_CR42","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, & Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"2575_CR43","doi-asserted-by":"crossref","unstructured":"Sun Y, Cheng C, Zhang Y, Zhang C, Zheng L, Wang Z, & Wei Y (2020) Circle loss: A unified perspective of pair similarity optimization. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6397\u20136406","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"2575_CR44","doi-asserted-by":"crossref","unstructured":"Thomas H, Qi CR, Deschaud J, Marcotegui B, Goulette F, & Guibas LJ (2019) Kpconv: Flexible and deformable convolution for point clouds. In: Proceedings of IEEE\/CVF International Conference on Computer Vision, pp 6410\u20136419","DOI":"10.1109\/ICCV.2019.00651"},{"issue":"6","key":"2575_CR45","doi-asserted-by":"publisher","first-page":"4581","DOI":"10.1109\/TRO.2023.3304239","volume":"39","author":"H Thomas","year":"2023","unstructured":"Thomas, H., Zhang, J., & Barfoot, T. D. (2023). The foreseeable future: Self-supervised learning to predict dynamic scenes for indoor navigation. IEEE Trans Robotics, 39(6), 4581\u20134599.","journal-title":"IEEE Trans Robotics"},{"issue":"4","key":"2575_CR46","doi-asserted-by":"publisher","first-page":"3575","DOI":"10.1109\/LRA.2018.2854290","volume":"3","author":"P Vechersky","year":"2018","unstructured":"Vechersky, P., Cox, M., Borges, P. V. K., & Lowe, T. (2018). Colourising point clouds using independent cameras. IEEE Robotics Autom Lett, 3(4), 3575\u20133582.","journal-title":"IEEE Robotics Autom Lett"},{"key":"2575_CR47","doi-asserted-by":"crossref","unstructured":"Wang B, Chen C, Cui Z, Qin J, Lu CX, Yu Z, Zhao P, Dong Z, Zhu F, Trigoni N, & Markham A (2021) P2-Net: Joint description and detection of local features for pixel and point matching. In: Proceedings of IEEE International Conference on Computer Vision, pp 15984\u201315993","DOI":"10.1109\/ICCV48922.2021.01570"},{"key":"2575_CR48","unstructured":"Wang H, Liu Y, Wang B, Sun Y, Dong Z, Wang W, & Yang B (2024) Freereg: Image-to-point cloud registration leveraging pretrained diffusion models and monocular depth estimators. In: Proceedings of International Conference on Learning Representation, pp 1\u201324"},{"key":"2575_CR49","unstructured":"Wang S, Li BZ, Khabsa M, Fang H, & Ma H (2020) Linformer: Self-attention with linear complexity. CoRR abs\/2006.04768"},{"key":"2575_CR50","doi-asserted-by":"crossref","unstructured":"Wu B, Ma J, Chen G, & An P (2021) Feature interactive representation for point cloud registration. In: Proceedings IEEE\/CVF International Conference on Computer Vision, pp 5510\u20135519","DOI":"10.1109\/ICCV48922.2021.00548"},{"key":"2575_CR51","first-page":"160","volume":"15123","author":"Q Wu","year":"2024","unstructured":"Wu, Q., Jiang, H., Luo, L., Li, J., Ding, Y., Xie, J., & Yang, J. (2024). Diff-reg: Diffusion model in doubly stochastic matrix space for registration problem. Proceedings of European Conference on Computer Vision, 15123, 160\u2013178.","journal-title":"Proceedings of European Conference on Computer Vision"},{"issue":"7","key":"2575_CR52","doi-asserted-by":"publisher","first-page":"4669","DOI":"10.1109\/TPAMI.2024.3360181","volume":"46","author":"Y Xu","year":"2024","unstructured":"Xu, Y., Lin, K., Zhang, G., Wang, X., & Li, H. (2024). Rnnpose: 6-dof object pose estimation via recurrent correspondence field estimation and pose optimization. IEEE Trans. Pattern Anal. Mach. Intell., 46(7), 4669\u20134683.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"2575_CR53","first-page":"2816","volume":"45","author":"H Yang","year":"2023","unstructured":"Yang, H., & Carlone, L. (2023). Certifiably optimal outlier-robust geometric perception: Semidefinite relaxations and scalable global optimization. IEEE Trans. Pattern Anal. Mach. Intell., 45(3), 2816\u20132834.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"2575_CR54","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1109\/TPAMI.2019.2960234","volume":"43","author":"J Yang","year":"2021","unstructured":"Yang, J., Xian, K., Wang, P., & Zhang, Y. (2021). A performance evaluation of correspondence grouping methods for 3d rigid data matching. IEEE Trans. Pattern Anal. Mach. Intell., 43(6), 1859\u20131874.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2575_CR55","doi-asserted-by":"crossref","unstructured":"Yao G, Xuan Y, Li X, & Pan Y (2024) Cmr-agent: Learning a cross-modal agent for iterative image-to-point cloud registration. In: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS, pp 13458\u201313465","DOI":"10.1109\/IROS58592.2024.10802594"},{"key":"2575_CR56","doi-asserted-by":"crossref","unstructured":"Ye H, Huang H, & Liu M (2020) Monocular direct sparse localization in a prior 3d surfel map. In: Proceedings of IEEE International Conference on Robotics and Automation, pp 8892\u20138898","DOI":"10.1109\/ICRA40945.2020.9197022"},{"issue":"1","key":"2575_CR57","first-page":"1","volume":"1","author":"H Yin","year":"2024","unstructured":"Yin, H., Xu, X., Lu, S., Chen, X., Xiong, R., Shen, S., Stachniss, C., & Wang, Y. (2024). A survey on global lidar localization: Challenges, advances and open problems. Int. J. Comput. Vis., 1(1), 1\u201333.","journal-title":"Int. J. Comput. Vis."},{"key":"2575_CR58","doi-asserted-by":"crossref","unstructured":"Yu H, Ye W, Feng Y, Bao H, & Zhang G (2020) Learning bipartite graph matching for robust visual localization. In: Proceedings of IEEE International Symposium on Mixed and Augmented Reality, pp 146\u2013155","DOI":"10.1109\/ISMAR50242.2020.00036"},{"issue":"4","key":"2575_CR59","doi-asserted-by":"publisher","first-page":"7517","DOI":"10.1109\/LRA.2021.3098923","volume":"6","author":"C Yuan","year":"2021","unstructured":"Yuan, C., Liu, X., Hong, X., & Zhang, F. (2021). Pixel-level extrinsic self calibration of high resolution lidar and camera in targetless environments. IEEE Robotics Autom Lett, 6(4), 7517\u20137524.","journal-title":"IEEE Robotics Autom Lett"},{"issue":"11","key":"2575_CR60","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/34.888718","volume":"22","author":"Z Zhang","year":"2000","unstructured":"Zhang, Z. (2000). A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell., 22(11), 1330\u20131334.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2575_CR61","unstructured":"Zhou J, Ma B, Zhang W, Fang Y, Liu Y, & Han Z (2023) Differentiable registration of images and lidar point clouds with voxelpoint-to-pixel matching. In: Proceedings of Advances in Neural Information Processing Systems, pp 1\u201310"},{"key":"2575_CR62","first-page":"407","volume":"13670","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q., Agostinho, S., Osep, A., & Leal-Taix\u00e9, L. (2022). Is geometry enough for matching in visual localization? Proceedings of European Conference on Computer Vision, 13670, 407\u2013425.","journal-title":"Proceedings of European Conference on Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02575-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02575-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02575-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:03:43Z","timestamp":1764993823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02575-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":62,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2575"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02575-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"18 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}