{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T06:37:27Z","timestamp":1772087847515,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Accurate six-degree-of-freedom (6-DoF) visual localization is a fundamental component for modern mapping and navigation. While recent data-centric approaches have leveraged Novel View Synthesis (NVS) to augment training datasets, these methods typically rely on uniform grid-based sampling of virtual cameras. Such naive placement often yields redundant or weakly informative views, failing to effectively bridge the gap between sparse, unordered captures and dense scene geometry. To address these challenges, we present LEGS (Visual Localization Enhanced by 3D Gaussian Splatting), a trajectory-agnostic synthetic-view augmentation framework. LEGS constructs a joint set of 6-DoF camera pose proposals by integrating a coarse 3D lattice with the Structure-from-Motion (SfM) camera graph, followed by a visibility-aware, coverage-driven selection strategy. By utilizing 3D Gaussian Splatting (3DGS), our framework enables high-throughput, scene-specific synthesis within practical computational budgets. Experiments on standard benchmarks and an in-house dataset demonstrate that LEGS consistently improves pose accuracy and robustness, particularly in scenarios characterized by sparse sampling and co-located viewpoints.<\/jats:p>","DOI":"10.3390\/jimaging12020084","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T09:22:46Z","timestamp":1771320166000},"page":"84","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LEGS: Visual Localization Enhanced by 3D Gaussian Splatting"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9436-3448","authenticated-orcid":false,"given":"Daewoon","family":"Kim","sequence":"first","affiliation":[{"name":"Tech. Innovation Group, KT Corporation, 151, Taebong-ro, Seocho-gu, Seoul 06763, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I-gil","family":"Kim","sequence":"additional","affiliation":[{"name":"Tech. Innovation Group, KT Corporation, 151, Taebong-ro, Seocho-gu, Seoul 06763, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., and Cipolla, R. (2015). PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization. Proceedings of the IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kendall, A., and Cipolla, R. (2016). Modelling uncertainty in deep learning for camera relocalization. 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA.2016.7487679"},{"key":"ref_3","unstructured":"Brachmann, E., Krull, A., Nowozin, S., Shotton, J., Michel, F., Gumhold, S., and Rother, C. (2017). Geometry-aware learning of maps for camera localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE."},{"key":"ref_4","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. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"ref_5","unstructured":"Xu, K., Jiang, Z., Cao, H., Yuan, S., Wang, C., and Xie, L. (2024). An efficient scene coordinate encoding and relocalization method. arXiv."},{"key":"ref_6","first-page":"1482","article-title":"Camera localization with Siamese neural networks using iterative relative pose estimation","volume":"9","author":"Kim","year":"2022","journal-title":"J. Comput. Des. Eng."},{"key":"ref_7","unstructured":"Moreau, A., Piasco, N., Tsishkou, D., Stanciulescu, B., and de La Fortelle, A. (2021). LENS: Localization Enhanced by NeRF Synthesis. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., and Frahm, J.-M. (2016). Structure-from-Motion Revisited. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592433","article-title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph. (SIGGRAPH)"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., and Rabinovich, A. (2018). SuperPoint: Self-Supervised Interest Point Detection and Description. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE.","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sarlin, P.-E., DeTone, D., Malisiewicz, T., and Rabinovich, A. (2020). SuperGlue: Learning Feature Matching with Graph Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.-E., and Pollefeys, M. (2023). LightGlue: Local Feature Matching at Light Speed. arXiv.","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref_13","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. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, J., Karaev, N., Rupprecht, C., and Novotny, D. (2024). VGGSfM: Visual geometry grounded deep structure from motion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Duisterhof, B., Zust, L., Weinzaepfel, P., Leroy, V., Cabon, Y., and Revaud, J. (2025). MASt3R-SfM: A fully-integrated solution for unconstrained structure-from-motion. 2025 International Conference on 3D Vision (3DV), IEEE.","DOI":"10.1109\/3DV66043.2025.00008"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., and Novotny, D. (2025). VGGT: Visual geometry grounded transformer. Proceedings of the Computer Vision and Pattern Recognition Conference, IEEE.","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Krull, A., Nowozin, S., Shotton, J., Michel, F., Gumhold, S., and Rother, C. (2017). DSAC: Differentiable RANSAC for camera localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.267"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Brachmann, E., and Rother, C. (2018). Learning less is more: 6D camera localization via 3D surface regression. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00489"},{"key":"ref_19","first-page":"3070","article-title":"Visual camera re-localization from RGB and RGB-D images using DSAC","volume":"43","author":"Brachmann","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","first-page":"405","article-title":"NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis","volume":"12346","author":"Mildenhall","year":"2020","journal-title":"Eur. Conf. Comput. Vis. (ECCV)"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S.M., Barron, J.T., Dosovitskiy, A., and Duckworth, D. (2021). NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., and Hedman, P. (2022). Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Srinivasan, P.P., Tancik, M., Verbin, D., and Hedman, P. (2023). Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref_24","first-page":"1","article-title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","volume":"43","author":"Kopanas","year":"2024","journal-title":"ACM Trans. Graph. (SIGGRAPH)"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cai, R., Tung, J., Wang, Q., Averbuch-Elor, H., Hariharan, B., and Snavely, N. (2023). Doppelgangers: Learning to disambiguate images of similar structures. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00010"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xiangli, Y., Cai, R., Chen, H., Byrne, J., and Snavely, N. (2024). Doppelgangers++: Improved visual disambiguation with geometric 3D features. Proceedings of the Computer Vision and Pattern Recognition Conference, IEEE.","DOI":"10.1109\/CVPR52734.2025.02530"},{"key":"ref_27","first-page":"303","article-title":"Enhancing Structure-from-Motion: Re-aligning images with 3D Gaussian splatting","volume":"13","author":"Kim","year":"2026","journal-title":"J. Comput. Des. Eng. (JCDE)"},{"key":"ref_28","unstructured":"Wu, C. (2026, February 12). VisualSFM: A Visual Structure from Motion System. Available online: http:\/\/ccwu.me\/vsfm\/doc.html."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shavit, Y., Ferens, R., and Keller, Y. (2021). Learning Multi-Scene Absolute Pose Regression with Transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00273"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/84\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:28:51Z","timestamp":1772083731000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/2\/84"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jimaging12020084"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12020084","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]}}}