{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:33Z","timestamp":1757608713221,"version":"3.44.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127668","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9740-9747","source":"Crossref","is-referenced-by-count":0,"title":["DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-Temporal Fusion"],"prefix":"10.1109","author":[{"given":"Mengmeng","family":"Liu","sequence":"first","affiliation":[{"name":"University of Twente,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael Ying","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Bath,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiuming","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"PhiGent Robotics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtao","family":"Li","sequence":"additional","affiliation":[{"name":"PhiGent Robotics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sander Oude","family":"Elberink","sequence":"additional","affiliation":[{"name":"University of Twente,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Vosselman","sequence":"additional","affiliation":[{"name":"University of Twente,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Twente,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01565"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"volume-title":"Og-gaussian: Occupancy based street gaussians for autonomous driving","year":"2025","author":"Shen","key":"ref3"},{"key":"ref4","article-title":"Real-time lidar point cloud compression and transmission for resource-constrained robots","author":"Cao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Compact 3d gaussian splatting for dense visual slam","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Deep patch visual odometry","volume":"36","author":"Teed","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548394"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02000"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3378829"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3415734"},{"key":"ref11","article-title":"Talk2radar: Bridging natural language with 4 d mmwave radar for 3 d referring expression comprehension","author":"Guan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240472"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594394"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196613"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163340"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262817"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3228492"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3330956"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_27"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.037"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-019-09881-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3207015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25256"},{"key":"ref24","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9525-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802599"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139486"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10010-w"},{"key":"ref29","first-page":"948","article-title":"Lip-loc: Lidar image pretraining for cross-modal localization","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Shubodh","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3210880"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01431"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01437"},{"key":"ref35","first-page":"13610","article-title":"Tap-vid: A benchmark for tracking any point in a video","volume":"35","author":"Doersch","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0901-7_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01876"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00867"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00776"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref42","article-title":"Unibevfusion: Unified radar-vision bevfusion for 3d object detection","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Achelous++: Power-oriented water-surface panoptic perception framework on edge devices based on vision-radar fusion and pruning of heterogeneous modalities","author":"Guan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01550"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref48","first-page":"1761","article-title":"Tartanvo: A generalizable learningbased vo","volume-title":"Conference on Robot Learning","author":"Wang","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2469274"},{"key":"ref50","article-title":"Dfvo: What should be learnt for visual odometry?","author":"Zhan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3241961"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00486"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981111"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636348"},{"volume-title":"A-LOAM: advanced implementation of loam","author":"Qin","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802130"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00389"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.005"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909895"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3215141"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.007"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127668.pdf?arnumber=11127668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:13Z","timestamp":1756879993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127668","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}