{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T15:11:32Z","timestamp":1774278692778,"version":"3.50.1"},"reference-count":61,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB4709802"],"award-info":[{"award-number":["2024YFB4709802"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373009"],"award-info":[{"award-number":["62373009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Guangdong S&T Program","doi-asserted-by":"publisher","award":["2024B0101050002"],"award-info":[{"award-number":["2024B0101050002"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Key Project of Pengcheng Laboratory","award":["PCL2024A01"],"award-info":[{"award-number":["PCL2024A01"]}]},{"name":"Mobile Information Networks-National Science and Technology Major Project","award":["2025ZD1302900"],"award-info":[{"award-number":["2025ZD1302900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Visual localization plays a critical role for mobile robots to estimate their position and orientation in GPS-denied environments. However, its efficiency, robustness, and generalization are fundamentally undermined by severe viewpoint changes and dramatic appearance variations, which present persistent challenges for image-based feature representation and pose estimation under real-world conditions. Recently, map-free visual relocalization (MFVR) has emerged as a promising paradigm for lightweight deployment and privacy isolation on edge devices, while how to learn compact and invariant image tokens without relying on structural 3D maps still remains a core problem, particularly in highly dynamic or long-term scenarios. In this paper, we propose the Debiased Multiplex Tokenizer as a novel method (termed as DMT-Loc) for efficient and versatile MFVR to address these issues. Specifically, DMT-Loc is built upon a pretrained vision Mamba encoder and integrates three key modules for relative pose regression: First, Multiplex Interactive Tokenization yields robust image tokens with non-local affinities and cross-domain descriptions. Second, Debiased Anchor Registration facilitates anchor token matching through proximity graph retrieval and autoregressive pointer attribution. Third, Geometry-Informed Pose Regression empowers multi-layer perceptrons with a symmetric swap gating mechanism operating inside each decoupled regression head to support accurate and flexible pose prediction in both pair-wise and multi-view modes. Extensive evaluations across seven public datasets demonstrate that DMT-Loc substantially outperforms existing baselines and ablation variants in diverse indoor and outdoor environments.<\/jats:p>","DOI":"10.3390\/make8030083","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T13:53:34Z","timestamp":1774274014000},"page":"83","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Debiased Multiplex Tokenization Using Mamba-Based Pointers for Efficient and Versatile Map-Free Visual Relocalization"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9012-6735","authenticated-orcid":false,"given":"Wenshuai","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University, Shenzhen 518055, China"},{"name":"Pengcheng Laboratory, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-6541","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4504-3659","authenticated-orcid":false,"given":"Shengquan","family":"Li","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9995-9812","authenticated-orcid":false,"given":"Peifeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9649-4313","authenticated-orcid":false,"given":"Dandan","family":"Che","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen 518055, China"},{"name":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4987-0405","authenticated-orcid":false,"given":"Runwei","family":"Ding","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6215","DOI":"10.1109\/TIP.2025.3607640","article-title":"Privacy-preserving visual localization with event cameras","volume":"34","author":"Kim","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.1109\/TIV.2024.3378716","article-title":"A survey on monocular re-Localization: From the perspective of scene map representation","volume":"10","author":"Miao","year":"2025","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_3","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., and Wang, X. (2024). Vision mamba: Efficient visual representation learning with bidirectional state space model. International Conference on Machine Learning, Association for Computing Machinery. PMLR."},{"key":"ref_4","unstructured":"Cho, J., Kim, J., Kim, J., Kim, M., Kang, M., Hong, S., Oh, T.H., and Yu, Y. (2025). DisCoRD: Discrete tokens to continuous motion via rectified flow decoding. IEEE International Conference on Computer Vision, IEEE."},{"key":"ref_5","first-page":"1","article-title":"Enhancing out-of-distribution generalization on graphs via causal attention learning","volume":"18","author":"Sui","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1353\/obs.2022.0007","article-title":"Causal Inference: History, perspectives, adventures, and unification (an interview with Judea Pearl)","volume":"8","author":"Pearl","year":"2022","journal-title":"Obs. Stud."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5336","DOI":"10.1007\/s10489-024-05343-y","article-title":"Non-local self-attention network for image super-resolution","volume":"54","author":"Zeng","year":"2024","journal-title":"Appl. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","article-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","volume":"42","author":"Malkov","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., and Fitzgibbon, A. (2013). Scene coordinate regression forests for camera relocalization in RGB-D images. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2013.377"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., and Cipolla, R. (2015). PoseNet: A convolutional network for real-time 6-DOF camera relocalization. IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, X., and Zhang, Y. (2023). Matrices over quaternion algebras. Matrix and Operator Equations and Applications, Springer.","DOI":"10.1007\/16618_2023_46"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., and Sivic, J. (2016). NetVLAD: CNN architecture for weakly supervised place recognition. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., and P\u00e9rez, P. (2010). Aggregating local descriptors into a compact image representation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yang, M., He, D., Fan, M., Shi, B., Xue, X., Li, F., Ding, E., and Huang, J. (2021). DOLG: Single-stage image retrieval with deep orthogonal fusion of local and global features. IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hausler, S., Garg, S., Xu, M., Milford, M., and Fischer, T. (2021). Patch-NetVLAD: Multi-scale fusion of locally-global descriptors for place recognition. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, R., Shen, Y., Zuo, W., Zhou, S., and Zheng, N. (2022). TransVPR: Transformer-based place recognition with multi-level attention aggregation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01328"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Berton, G., Masone, C., and Caputo, B. (2022). Rethinking visual geo-localization for large-scale applications. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., and Giguere, P. (2023). MixVPR: Feature mixing for visual place recognition. IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Izquierdo, S., and Civera, J. (2024). Optimal transport aggregation for visual place recognition. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"ref_20","unstructured":"Lu, F., Zhang, L., Lan, X., Dong, S., Wang, Y., and Yuan, C. (2024). Towards seamless adaptation of pre-trained models for visual place recognition. International Conference on Learning Representations, ICLR."},{"key":"ref_21","unstructured":"Tzachor, I., Lerner, B., Levy, M., Green, M., Shalev, T.B., Habib, G., Samuel, D., Zailer, N.K., Shimshi, O., and Darshan, N. (2025). EffoVPR: Effective foundation model utilization for visual place recognition. International Conference on Learning Representations, ICLR."},{"key":"ref_22","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). DINOv2: Learning robust visual features without supervision. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2016.2611662","article-title":"Efficient and effective prioritized matching for large-scale image-based localization","volume":"39","author":"Sattler","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Giang, K.T., Song, S., and Jo, S. (2024). Learning to produce semi-dense correspondences for visual localization. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01841"},{"key":"ref_25","first-page":"5847","article-title":"Visual camera re-localization from RGB and RGB-D images using DSAC","volume":"44","author":"Brachmann","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Cavallari, T., and Prisacariu, V.A. (2023). Accelerated coordinate encoding: Learning to relocalize in minutes using RGB and poses. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3586","DOI":"10.1109\/LRA.2024.3364449","article-title":"SACNet: A scattered attention-based network with feature compensator for visual localization","volume":"9","author":"Wang","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_28","unstructured":"Moreau, A., Piasco, N., Tsishkou, D., Stanciulescu, B., and de La Fortelle, A. (2022). Lens: Localization enhanced by nerf synthesis. Conference on Robot Learning; PMLR, Association for Computing Machinery."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Chen, S., Cavallari, T., Prisacariu, V.A., and Brachmann, E. (2024). Map-relative pose regression for visual re-localization. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01953"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., and Dymczyk, M. (2019). From coarse to fine: Robust hierarchical localization at large scale. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref_31","unstructured":"Saha, S., Varma, G., and Jawahar, C.V. (2018). Improved visual relocalization by discovering anchor points. British Machine Vision Conference, BMVA Press."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Laskar, Z., Melekhov, I., Kalia, S., and Kannala, J. (2017). Camera relocalization by computing pairwise relative poses using convolutional neural network. IEEE International Conference on Computer Vision Workshops, IEEE.","DOI":"10.1109\/ICCVW.2017.113"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Balntas, V., Li, S., and Prisacariu, V. (2018). RelocNet: Continuous metric learning relocalisation using neural nets. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Sattler, T., Pollefeys, M., and Leal-Taixe, L. (2020). To learn or not to learn: Visual localization from essential matrices. IEEE International Conference on Robotics and Automation, IEEE.","DOI":"10.1109\/ICRA40945.2020.9196607"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"104629","DOI":"10.1016\/j.cviu.2025.104629","article-title":"Beyond familiar landscapes: Exploring the limits of relative pose regressors in new environments","volume":"264","author":"Idan","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Turkoglu, M.O., Brachmann, E., Schindler, K., Brostow, G.J., and Monszpart, A. (2021). Visual camera re-localization using graph neural networks and relative pose supervision. IEEE International Conference on 3D Vision, IEEE.","DOI":"10.1109\/3DV53792.2021.00025"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Dong, S., Wang, S., Liu, S., Cai, L., Fan, Q., Kannala, J., and Yang, Y. (2025). Reloc3r: Large-scale training of relative camera pose regression for generalizable, fast, and accurate visual localization. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52734.2025.01560"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., and Revaud, J. (2024). Dust3r: Geometric 3D vision made easy. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref_39","unstructured":"Martins, A., and Astudillo, R. (2016). From softmax to sparsemax: A sparse model of attention and multi-label classification. International Conference on Machine Learning, Association for Computing Machinery. PMLR."},{"key":"ref_40","first-page":"10221","article-title":"Beyond spatial domain: Cross-domain promoted fourier convolution helps single image dehazing","volume":"39","author":"Zhang","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Taira, H., Okutomi, M., Sattler, T., Cimpoi, M., Pollefeys, M., Sivic, J., Pajdla, T., and Torii, A. (2018). InLoc: Indoor visual localization with dense matching and view synthesis. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00752"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1109\/TPAMI.2020.3032010","article-title":"Long-term visual localization revisited","volume":"44","author":"Toft","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Warburg, F., Hauberg, S., Lopez-Antequera, M., Gargallo, P., Kuang, Y., and Civera, J. (2020). Mapillary street-level sequences: A dataset for lifelong place recognition. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"ref_44","unstructured":"S\u00fcnderhauf, N., Neubert, P., and Protzel, P. (2013). Are we there yet? Challenging SeqSLAM on a 3000 km journey across all four seasons. IEEE International Conference on Robotics and Automation, IEEE."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., and Kautz, J. (2025). MambaVision: A hybrid mamba-transformer vision backbone. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"123087","DOI":"10.1109\/ACCESS.2020.3007337","article-title":"Radial basis function networks for convolutional neural networks to learn similarity distance metric and improve interpretability","volume":"8","author":"Amirian","year":"2020","journal-title":"IEEE Access"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Unagar, A., Larsson, M., Germain, H., Toft, C., Larsson, V., Pollefeys, M., Lepetit, V., Hammarstrand, L., and Kahl, F. (2021). Back to the feature: Learning robust camera localization from pixels to pose. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Polizzi, V., Cannici, M., Scaramuzza, D., and Kelly, J. (2025). FaVoR: Features via voxel rendering for camera relocalization. IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV61041.2025.00015"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Tang, S., Tang, S., Tagliasacchi, A., Tan, P., and Furukawa, Y. (2023). Neumap: Neural coordinate mapping by auto-transdecoder for camera localization. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.00096"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"2530","DOI":"10.1007\/s11263-023-01982-9","article-title":"HSCNet++: Hierarchical scene coordinate classification and regression for visual localization with transformer","volume":"132","author":"Wang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"11449","DOI":"10.1109\/LRA.2024.3487503","article-title":"D2S: Representing sparse descriptors and 3D coordinates for camera relocalization","volume":"9","author":"Bui","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Shavit, Y., and Keller, Y. (2022). Camera pose auto-encoders for improving pose regression. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-20080-9_9"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Chen, S., Li, X., Wang, Z., and Prisacariu, V.A. (2022). Dfnet: Enhance absolute pose regression with direct feature matching. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-20080-9_1"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Lin, J., Gu, J., Wu, B., Fan, L., Chen, R., Liu, L., and Ye, J. (2024). Learning neural volumetric pose features for camera localization. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-72995-9_12"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Arnold, E., Wynn, J., Vicente, S., Garcia-Hernando, G., Monszpart, A., Prisacariu, V., Turmukhambetov, D., and Brachmann, E. (2022). Map-free visual relocalization: Metric pose relative to a single image. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Ding, M., Wang, Z., Sun, J., Shi, J., and Luo, P. (2019). CamNet: Coarse-to-fine retrieval for camera re-localization. IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00296"},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Sattler, T., Zhou, Q., Pollefeys, M., and Leal-Taixe, L. (2019). Understanding the limitations of CNN-based absolute camera pose regression. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00342"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Sivic, J., Torii, A., and Sattler, T. (2019). D2-net: A trainable CNN for joint description and detection of local features. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00828"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Ram, P., and Sinha, K. (2019). Revisiting kd-tree for nearest neighbor search. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/3292500.3330875"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/MSP.2007.914237","article-title":"Locality-sensitive hashing for finding nearest neighbors","volume":"25","author":"Slaney","year":"2008","journal-title":"IEEE Signal Process. Mag."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/3\/83\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T14:25:31Z","timestamp":1774275931000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/3\/83"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":61,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["make8030083"],"URL":"https:\/\/doi.org\/10.3390\/make8030083","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]}}}