{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:14:38Z","timestamp":1768414478876,"version":"3.49.0"},"reference-count":68,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T00:00:00Z","timestamp":1681344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013145","name":"Primary Research and Development Plan of Zhejiang Province","doi-asserted-by":"publisher","award":["2021C01196"],"award-info":[{"award-number":["2021C01196"]}],"id":[{"id":"10.13039\/501100013145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to the complementary characteristics of visual and LiDAR information, these two modalities have been fused to facilitate many vision tasks. However, current studies of learning-based odometries mainly focus on either the visual or LiDAR modality, leaving visual\u2013LiDAR odometries (VLOs) under-explored. This work proposes a new method to implement an unsupervised VLO, which adopts a LiDAR-dominant scheme to fuse the two modalities. We, therefore, refer to it as unsupervised vision-enhanced LiDAR odometry (UnVELO). It converts 3D LiDAR points into a dense vertex map via spherical projection and generates a vertex color map by colorizing each vertex with visual information. Further, a point-to-plane distance-based geometric loss and a photometric-error-based visual loss are, respectively, placed on locally planar regions and cluttered regions. Last, but not least, we designed an online pose-correction module to refine the pose predicted by the trained UnVELO during test time. In contrast to the vision-dominant fusion scheme adopted in most previous VLOs, our LiDAR-dominant method adopts the dense representations for both modalities, which facilitates the visual\u2013LiDAR fusion. Besides, our method uses the accurate LiDAR measurements instead of the predicted noisy dense depth maps, which significantly improves the robustness to illumination variations, as well as the efficiency of the online pose correction. The experiments on the KITTI and DSEC datasets showed that our method outperformed previous two-frame-based learning methods. It was also competitive with hybrid methods that integrate a global optimization on multiple or all frames.<\/jats:p>","DOI":"10.3390\/s23083967","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T02:03:38Z","timestamp":1681437818000},"page":"3967","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["UnVELO: Unsupervised Vision-Enhanced LiDAR Odometry with Online Correction"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3253-378X","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0969-7248","authenticated-orcid":false,"given":"Haifeng","family":"Ye","sequence":"additional","affiliation":[{"name":"Faculty of the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9176-5962","authenticated-orcid":false,"given":"Sihan","family":"Fu","sequence":"additional","affiliation":[{"name":"Faculty of the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9955-3569","authenticated-orcid":false,"given":"Xiaojin","family":"Gong","sequence":"additional","affiliation":[{"name":"Faculty of the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyu","family":"Xiang","sequence":"additional","affiliation":[{"name":"Faculty of the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, A.W., Meng, T., Caine, B., Ngiam, J., Peng, D., Shen, J., Lu, Y., Zhou, D., and Le, Q.V. (2022, January 19\u201324). DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection. Proceedings of the CVPR, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., and Beijbom, O. (2020, January 13\u201319). PointPainting: Sequential Fusion for 3D Object Detection. Proceedings of the CVPR, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., and Radha, H. (2022, January 4\u20138). Fast-CLOCs: Fast Camera-LiDAR Object Candidates Fusion for 3D Object Detection. Proceedings of the WACV, Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00380"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ma, F., and Karaman, S. (2018, January 21\u201325). Sparse-to-dense: Depth prediction from sparse depth samples and a single image. Proceedings of the ICRA, Brisbane, QLD, Australia.","DOI":"10.1109\/ICRA.2018.8460184"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hua, J., and Gong, X. (2018, January 13\u201319). A normalized convolutional neural network for guided sparse depth upsampling. Proceedings of the IJCAI, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/316"},{"key":"ref_6","unstructured":"Hu, M., Wang, S., Li, B., Ning, S., Fan, L., and Gong, X. (June, January 30). Penet: Towards precise and efficient image guided depth completion. Proceedings of the ICRA, Xi\u2019an, China."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rishav, R., Battrawy, R., Schuster, R., Wasenm\u00fcller, O., and Stricker, D. (2020, January 25\u201329). DeepLiDARFlow: A deep learning architecture for scene flow estimation using monocular camera and sparse LiDAR. Proceedings of the IROS, Las Vegas, NV, USA.","DOI":"10.1109\/IROS45743.2020.9341077"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, H., Lu, T., Xu, Y., Liu, J., Li, W., and Chen, L. (2022, January 19\u201324). CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation. Proceedings of the CVPR, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, R., Pizer, S.M., and Frahm, J.M. (2019, January 16\u201320). Recurrent Neural Network for (Un-)supervised Learning of Monocular Video Visual Odometry and Depth. Proceedings of the CVPR, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00570"},{"key":"ref_10","unstructured":"Bian, J., Li, Z., Wang, N., Zhan, H., Shen, C., Cheng, M., and Reid, I. (2019, January 8\u201314). Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video. Proceedings of the NIPS, Vancouver, BC, Canada."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Xiong, M., Zhang, Z., Zhong, W., Ji, J., Liu, J., and Xiong, H. (2020, January 7\u201315). Self-supervised Monocular Depth and Visual Odometry Learning with Scale-consistent Geometric Constraints. Proceedings of the IJCAI, Online.","DOI":"10.24963\/ijcai.2020\/134"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4431","DOI":"10.1109\/LRA.2019.2925555","article-title":"SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation With Stacked Generative Adversarial Networks","volume":"4","author":"Feng","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, X., Hou, Y., Wu, Q., Wang, P., and Li, W. (2019, January 1\u20134). Dvonet: Unsupervised monocular depth estimation and visual odometry. Proceedings of the VCIP, Sydney, Australia.","DOI":"10.1109\/VCIP47243.2019.8965952"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, S., Wang, X., Cao, Y., Xue, F., Yan, Z., and Zha, H. (2020, January 13\u201319). Self-Supervised Deep Visual Odometry with Online Adaptation. Proceedings of the CVPR, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00637"},{"key":"ref_15","unstructured":"Zhang, J., Sui, W., Wang, X., Meng, W., Zhu, H., and Zhang, Q. (June, January 30). Deep Online Correction for Monocular Visual Odometry. Proceedings of the ICRA, Xi\u2019an, China."},{"key":"ref_16","unstructured":"Chen, Y., Schmid, C., and Sminchisescu, C. (November, January 27). Self-Supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera. Proceedings of the ICCV, Seoul, Republic of Korea."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, Q., Chen, S., Wang, C., Li, X., Wen, C., Cheng, M., and Li, J. (2019, January 16\u201320). LO-Net: Deep Real-Time Lidar Odometry. Proceedings of the CVPR, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00867"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Cho, Y., Kim, G., and Kim, A. (August, January 31). Unsupervised Geometry-Aware Deep LiDAR Odometry. Proceedings of the ICRA, Paris, France.","DOI":"10.1109\/ICRA40945.2020.9197366"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"47","DOI":"10.5194\/isprs-annals-V-1-2021-47-2021","article-title":"Deeplio: Deep Lidar Inertial Sensor Fusion for Odometry Estimation","volume":"V-1-2021","author":"Iwaszczuk","year":"2021","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_20","unstructured":"Nubert, J., Khattak, S., and Hutter, M. (June, January 30). Self-supervised learning of lidar odometry for robotic applications. Proceedings of the ICRA, Xi\u2019an, China."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, G., Wu, X., Jiang, S., Liu, Z., and Wang, H. (2021). Efficient 3D Deep LiDAR Odometry. arXiv.","DOI":"10.1109\/TPAMI.2022.3207015"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lu, W., Zhou, Y., Wan, G., Hou, S., and Song, S. (2019, January 16\u201320). L3-net: Towards learning based lidar localization for autonomous driving. Proceedings of the CVPR, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00655"},{"key":"ref_23","unstructured":"Lu, W., Wan, G., Zhou, Y., Fu, X., Yuan, P., and Song, S. (November, January 27). DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration. Proceedings of the ICCV, Seoul, Republic of Korea."},{"key":"ref_24","unstructured":"Xu, Y., Huang, Z., Lin, K.Y., Zhu, X., Shi, J., Bao, H., Zhang, G., and Li, H. (2020, January 16\u201318). SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks. Proceedings of the CoRL, Online."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, G., Wu, X., Liu, Z., and Wang, H. (2021, January 19\u201325). Pwclo-net: Deep lidar odometry in 3d point clouds using hierarchical embedding mask optimization. Proceedings of the CVPR, Virtual.","DOI":"10.1109\/CVPR46437.2021.01565"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1109\/LRA.2022.3140794","article-title":"Robust self-supervised lidar odometry via representative structure discovery and 3d inherent error modeling","volume":"7","author":"Xu","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, B., Hu, M., Wang, S., Wang, L., and Gong, X. (2021, January 5\u20139). Self-supervised Visual-LiDAR Odometry with Flip Consistency. Proceedings of the WACV, Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00389"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, Q., Zhang, H., Xu, Y., and Wang, L. (2020). Unsupervised Deep Learning-Based RGB-D Visual Odometry. Appl. Sci., 10.","DOI":"10.3390\/app10165426"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1007\/s12559-022-10010-w","article-title":"Visual-LiDAR SLAM Based on Unsupervised Multi-channel Deep Neural Networks","volume":"14","author":"An","year":"2022","journal-title":"Cogn. Comput."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"11654","DOI":"10.1109\/TITS.2021.3106055","article-title":"Self-Supervised Depth Completion From Direct Visual-LiDAR Odometry in Autonomous Driving","volume":"23","author":"Song","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., and Cremers, D. (2012, January 7\u201312). A benchmark for the evaluation of RGB-D SLAM systems. Proceedings of the IROS, Algarve, Portugal.","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Singh, S. (2014, January 12\u201316). LOAM: Lidar Odometry and Mapping in Real-time. Proceedings of the RSS 2014\u2014Robotics: Science and Systems Conference, Berkeley, CA, USA.","DOI":"10.15607\/RSS.2014.X.007"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Klein, G., and Murray, D. (2007, January 13\u201316). Parallel tracking and mapping for small AR workspaces. Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, Nara, Japan.","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1109\/TAES.2016.140829","article-title":"Radar odometry with recursive-RANSAC","volume":"52","author":"Quist","year":"2016","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Singh, S. (2015, January 26\u201330). Visual-lidar odometry and mapping: Low-drift, robust, and fast. Proceedings of the ICRA, Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139486"},{"key":"ref_36","first-page":"1","article-title":"SOFT2: Stereo Visual Odometry for Road Vehicles Based on a Point-to-Epipolar-Line Metric","volume":"23","year":"2022","journal-title":"IEEE Trans. Robot."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., and Lowe, D.G. (2017, January 21\u201326). Unsupervised learning of depth and ego-motion from video. Proceedings of the CVPR, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1007\/s13042-019-01020-6","article-title":"Unsupervised learning of monocular depth and ego-motion with space\u2013temporal-centroid loss","volume":"11","author":"Zhang","year":"2020","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Yin, X., Wang, X., Du, X., and Chen, Q. (2017, January 22\u201329). Scale Recovery for Monocular Visual Odometry Using Depth Estimated with Deep Convolutional Neural Fields. Proceedings of the ICCV, Venice, Italy.","DOI":"10.1109\/ICCV.2017.625"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1007\/s00371-019-01714-6","article-title":"A review of monocular visual odometry","volume":"36","author":"He","year":"2020","journal-title":"Vis. Comput."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, S., Long, Z., and Gu, D. (2018, January 21\u201325). UnDeepVO: Monocular Visual Odometry Through Unsupervised Deep Learning. Proceedings of the ICRA, Brisbane, QLD, Australia.","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yin, Z., and Shi, J. (2018, January 18\u201322). GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose. Proceedings of the 2018 Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Yang, N., Wang, R., Stuckler, J., and Cremers, D. (2018, January 8\u201314). Deep virtual stereo odometry: Leveraging deep depth prediction for monocular direct sparse odometry. Proceedings of the ECCV, Munich, Germany.","DOI":"10.1007\/978-3-030-01237-3_50"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Yang, N., Stumberg, L., Wang, R., and Cremers, D. (2020, January 13\u201319). D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry. Proceedings of the CVPR, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00136"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Li, Z., and Wang, N. (2020, January 24). Dmlo: Deep matching lidar odometry. Proceedings of the IROS, Las Vegas, NV, USA.","DOI":"10.1109\/IROS45743.2020.9341206"},{"key":"ref_46","unstructured":"Tu, Y. (2022). UnPWC-SVDLO: Multi-SVD on PointPWC for Unsupervised Lidar Odometry. arXiv."},{"key":"ref_47","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the CVPR, Honolulu, HI, USA."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/TPAMI.1987.4767965","article-title":"Least-squares fitting of two 3-D point sets","volume":"PAMI-9","author":"Arun","year":"1987","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_49","unstructured":"Segal, A., Haehnel, D., and Thrun, S. (July, January 28). Generalized-icp. Proceedings of the Robotics: Science and Systems V, Seattle, WA, USA."},{"key":"ref_50","unstructured":"Serafin, J., and Grisetti, G. (October, January 28). NICP: Dense normal based point cloud registration. Proceedings of the IROS, Hamburg, Germany."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"17298806221078669","DOI":"10.1177\/17298806221078669","article-title":"Self-supervised learning of LiDAR odometry based on spherical projection","volume":"19","author":"Fu","year":"2022","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Tibebu, H., De-Silva, V., Artaud, C., Pina, R., and Shi, X. (2022). Towards Interpretable Camera and LiDAR Data Fusion for Autonomous Ground Vehicles Localisation. Sensors, 22.","DOI":"10.20944\/preprints202209.0276.v1"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Wang, C., Ma, C., Zhu, M., and Yang, X. (2021, January 19\u201325). Pointaugmenting: Cross-modal augmentation for 3d object detection. Proceedings of the CVPR, Virtual.","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref_54","unstructured":"Casser, V., Pirk, S., Mahjourian, R., and Angelova, A. (February, January 27). Depth prediction without the sensors: Leveraging structure for unsupervised learning from monocular videos. Proceedings of the AAAI, Honolulu, HI, USA."},{"key":"ref_55","unstructured":"McCraith, R., Neumann, L., Zisserman, A., and Vedaldi, A. (2020). Monocular depth estimation with self-supervised instance adaptation. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Hong, S., and Kim, S. (2021, January 10\u201317). Deep Matching Prior: Test-Time Optimization for Dense Correspondence. Proceedings of the ICCV, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00976"},{"key":"ref_57","unstructured":"Zhu, W., Huang, Y., Xu, D., Qian, Z., Fan, W., and Xie, X. (June, January 30). Test-Time Training for Deformable Multi-Scale Image Registration. Proceedings of the ICRA, Xi\u2019an, China."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Li, S., Wu, X., Cao, Y., and Zha, H. (2021, January 19\u201325). Generalizing to the Open World: Deep Visual Odometry with Online Adaptation. Proceedings of the CVPR, Virtual.","DOI":"10.1109\/CVPR46437.2021.01298"},{"key":"ref_59","unstructured":"Golub, G.H., and Van Loan, C.F. (1996). Matrix Computations, The Johns Hopkins University Press."},{"key":"ref_60","unstructured":"Kingma, D., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Suh, Y., Han, B., Kim, W., and Lee, K.M. (2019, January 16\u201320). Stochastic Class-based Hard Example Mining for Deep Metric Learning. Proceedings of the CVPR, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00742"},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.neucom.2019.11.094","article-title":"Hard sample mining makes person re-identification more efficient and accurate","volume":"382","author":"Chen","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16\u201321). Are we ready for autonomous driving? the KITTI vision benchmark suite. Proceedings of the CVPR, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"4947","DOI":"10.1109\/LRA.2021.3068942","article-title":"Dsec: A stereo event camera dataset for driving scenarios","volume":"6","author":"Gehrig","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_65","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the NIPS, Vancouver, BC, Canada."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"6766","DOI":"10.1109\/LRA.2022.3176087","article-title":"On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion","volume":"7","author":"Wagstaff","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_67","unstructured":"Wagstaff, B., Peretroukhin, V., and Kelly, J. (August, January 31). Self-supervised deep pose corrections for robust visual odometry. Proceedings of the ICRA, Paris, France."},{"key":"ref_68","unstructured":"Tu, Y., and Xie, J. (2021, January 9\u201312). UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry. Proceedings of the 6th Asian Conference on Pattern Recognition\u2014ACPR 2021, Jeju Island, Republic of Korea."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/3967\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:15:48Z","timestamp":1760123748000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/3967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,13]]},"references-count":68,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23083967"],"URL":"https:\/\/doi.org\/10.3390\/s23083967","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,13]]}}}