{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T10:45:38Z","timestamp":1782816338284,"version":"3.54.5"},"reference-count":103,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.neucom.2026.133023","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T16:48:51Z","timestamp":1770828531000},"page":"133023","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["D3FlowSLAM: Self-supervised dynamic SLAM with flow motion decomposition and DINO guidance"],"prefix":"10.1016","volume":"677","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1081-7033","authenticated-orcid":false,"given":"Xingyuan","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weicai","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyue","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4548-6388","authenticated-orcid":false,"given":"Yuhang","family":"Ming","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-8600","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaopeng","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5661-8430","authenticated-orcid":false,"given":"Guofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133023_bib0005","series-title":"IEEE Virtual Reality and 3D User Interfaces","article-title":"SuperPlane: 3D plane detection and description from a single image","author":"Ye","year":"2021"},{"key":"10.1016\/j.neucom.2026.133023_bib0010","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1109\/LRA.2020.3045647","article-title":"Dymslam: 4D dynamic scene reconstruction based on geometrical motion segmentation","volume":"6","author":"Wang","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133023_bib0015","article-title":"DGS-SLAM: a fast and robust RGBD SLAM in dynamic environments combined by geometric and semantic information","volume":"14","author":"Yan","year":"2022","journal-title":"Remote Sens."},{"key":"10.1016\/j.neucom.2026.133023_bib0020","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"1168","article-title":"DS-SLAM: a semantic visual SLAM towards dynamic environments","author":"Yu","year":"2018"},{"issue":"1","key":"10.1016\/j.neucom.2026.133023_bib0025","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/TPAMI.2020.3010942","article-title":"RGB-D SLAM in dynamic environments using point correlations","volume":"44","author":"Dai","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133023_bib0030","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2123","article-title":"Dynamic SLAM: the need for speed","author":"Henein","year":"2020"},{"issue":"4","key":"10.1016\/j.neucom.2026.133023_bib0035","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","article-title":"VINS-Mono: a robust and versatile monocular visual-inertial state estimator","volume":"34","author":"Qin","year":"2018","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133023_bib0040","doi-asserted-by":"crossref","first-page":"4378","DOI":"10.1109\/TCSVT.2023.3335989","article-title":"Ct-LVI: a framework towards continuous-time laser-visual-inertial odometry and mapping","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133023_bib0045","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1109\/TCSVT.2024.3482573","article-title":"DFF-VIO: a general dynamic feature fused monocular visual-inertial odometry","volume":"35","author":"Luo","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133023_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129017","article-title":"A new visual-inertial odometry scheme for unmanned systems in unified framework of zeroing neural networks","volume":"617","author":"Chen","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133023_bib0055","series-title":"ECCV","article-title":"LSD-SLAM: large-scale direct monocular SLAM","author":"Engel","year":"2014"},{"issue":"5","key":"10.1016\/j.neucom.2026.133023_bib0060","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"ORB-SLAM: a versatile and accurate monocular SLAM system","volume":"31","author":"Mur-Artal","year":"2015","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133023_bib0065","series-title":"ICRA","first-page":"15","article-title":"SVO: fast semi-direct monocular visual odometry","author":"Forster","year":"2014"},{"issue":"3","key":"10.1016\/j.neucom.2026.133023_bib0070","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","article-title":"Direct sparse odometry","volume":"40","author":"Engel","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133023_bib0075","series-title":"Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Unsupervised learning of depth and ego-motion from video","author":"Zhou","year":"2017"},{"issue":"4\u20135","key":"10.1016\/j.neucom.2026.133023_bib0080","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1177\/0278364917734298","article-title":"End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks","volume":"37","author":"Wang","year":"2018","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.neucom.2026.133023_bib0085","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"970","article-title":"Improving learning-based ego-motion estimation with homomorphism-based losses and drift correction","author":"Wang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133023_bib0090","series-title":"International Conference on Advanced Robotics (ICAR)","first-page":"83","article-title":"Non-iterative SLAM","author":"Wang","year":"2017"},{"key":"10.1016\/j.neucom.2026.133023_bib0095","author":"Wang"},{"key":"10.1016\/j.neucom.2026.133023_bib0100","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Geometry-aware learning of maps for camera localization","author":"Brahmbhatt","year":"2018"},{"key":"10.1016\/j.neucom.2026.133023_bib0105","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6243","article-title":"CNN-SLAM: real-time dense monocular SLAM with learned depth prediction","author":"Tateno","year":"2017"},{"issue":"2","key":"10.1016\/j.neucom.2026.133023_bib0110","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/LRA.2020.2965415","article-title":"DeepFactors: real-time probabilistic dense monocular SLAM","volume":"5","author":"Czarnowski","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133023_bib0115","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neucom.2019.01.088","article-title":"ObjectFusion: an object detection and segmentation framework with RGB-D SLAM and convolutional neural networks","volume":"345","author":"Tian","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133023_bib0120","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.neucom.2020.02.044","article-title":"DRM-SLAM: towards dense reconstruction of monocular slam with scene depth fusion","volume":"396","author":"Ye","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133023_bib0125","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.neucom.2021.05.027","article-title":"Lift-SLAM: a deep-learning feature-based monocular visual SLAM method","volume":"455","author":"Bruno","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133023_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129041","article-title":"Monocular thermal SLAM with neural radiance fields for 3D scene reconstruction","volume":"617","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133023_bib0135","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12786","article-title":"Nice-SLAM: neural implicit scalable encoding for SLAM","author":"Zhu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133023_bib0140","series-title":"2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)","first-page":"499","article-title":"Vox-Fusion: dense tracking and mapping with voxel-based neural implicit representation","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133023_bib0145","first-page":"16558","article-title":"DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras","volume":"34","author":"Teed","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133023_bib0150","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Unflow: unsupervised learning of optical flow with a bidirectional census loss","volume":"vol. 32","author":"Meister","year":"2018"},{"key":"10.1016\/j.neucom.2026.133023_bib0155","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1045","article-title":"Upflow: upsampling pyramid for unsupervised optical flow learning","author":"Luo","year":"2021"},{"key":"10.1016\/j.neucom.2026.133023_bib0160","series-title":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","first-page":"1","article-title":"Optical-flow-aided self-supervised single view depth estimation from monocular videos","author":"Bello","year":"2023"},{"key":"10.1016\/j.neucom.2026.133023_bib0165","series-title":"European Conference on Computer Vision","first-page":"228","article-title":"Disentangling object motion and occlusion for unsupervised multi-frame monocular depth","author":"Feng","year":"2022"},{"key":"10.1016\/j.neucom.2026.133023_bib0170","article-title":"Dynamo-depth: fixing unsupervised depth estimation for dynamical scenes","volume":"36","author":"Sun","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.neucom.2026.133023_bib0175","doi-asserted-by":"crossref","first-page":"1776","DOI":"10.1109\/TCSVT.2022.3215587","article-title":"3D hierarchical refinement and augmentation for unsupervised learning of depth and pose from monocular video","volume":"33","author":"Wang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"10.1016\/j.neucom.2026.133023_bib0180","doi-asserted-by":"crossref","first-page":"1751","DOI":"10.1109\/TCSVT.2021.3080928","article-title":"Depth estimation using a self-supervised network based on cross-layer feature fusion and the quadtree constraint","volume":"32","author":"Tian","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"10.1016\/j.neucom.2026.133023_bib0185","doi-asserted-by":"crossref","first-page":"4076","DOI":"10.1109\/LRA.2018.2860039","article-title":"DynaSLAM: tracking, mapping, and inpainting in dynamic scenes","volume":"3","author":"Bescos","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133023_bib0190","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.robot.2019.03.012","article-title":"Dynamic-SLAM: semantic monocular visual localization and mapping based on deep learning in dynamic environment","volume":"117","author":"Xiao","year":"2019","journal-title":"Robot. Auton. Syst."},{"issue":"4","key":"10.1016\/j.neucom.2026.133023_bib0195","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1109\/TRO.2019.2909168","article-title":"CubeSLAM: monocular 3-d object SLAM","volume":"35","author":"Yang","year":"2019","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133023_bib0200","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2168","article-title":"Clustervo: clustering moving instances and estimating visual odometry for self and surroundings","author":"Huang","year":"2020"},{"issue":"7","key":"10.1016\/j.neucom.2026.133023_bib0205","doi-asserted-by":"crossref","first-page":"4788","DOI":"10.1109\/TCSVT.2021.3135041","article-title":"Mofis SLAM: a multi-object semantic SLAM system with front-view, inertial, and surround-view sensors for indoor parking","volume":"32","author":"Shao","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133023_bib0210","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"7322","article-title":"Flowfusion: dynamic dense RGB-D SLAM based on optical flow","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0215","author":"Zhan"},{"key":"10.1016\/j.neucom.2026.133023_bib0220","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"issue":"3","key":"10.1016\/j.neucom.2026.133023_bib0225","first-page":"4","article-title":"Deep vit features as dense visual descriptors","volume":"2","author":"Amir","year":"2021","journal-title":"arXiv preprint"},{"key":"10.1016\/j.neucom.2026.133023_bib0230","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0235","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neucom.2026.133023_bib0240","author":"Oquab"},{"key":"10.1016\/j.neucom.2026.133023_bib0245","series-title":"2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)","first-page":"209","article-title":"Robust monocular SLAM in dynamic environments","author":"Tan","year":"2013"},{"key":"10.1016\/j.neucom.2026.133023_bib0250","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"4942","article-title":"Dual-SLAM: a framework for robust single camera navigation","author":"Huang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0255","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.neucom.2026.133023_bib0260","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"4974","article-title":"Dynamic object tracking and masking for visual SLAM","author":"Vincent","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0265","series-title":"2020 IEEE Intelligent Vehicles Symposium (IV)","first-page":"651","article-title":"Multi-object monocular SLAM for dynamic environments","author":"Nair","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0270","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9579","article-title":"PVO: panoptic visual odometry","author":"Ye","year":"2023"},{"key":"10.1016\/j.neucom.2026.133023_bib0275","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5865","article-title":"Em-fusion: dynamic object-level SLAM with probabilistic data association","author":"Strecke","year":"2019"},{"key":"10.1016\/j.neucom.2026.133023_bib0280","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"393","article-title":"Semantic monocular SLAM for highly dynamic environments","author":"Brasch","year":"2018"},{"key":"10.1016\/j.neucom.2026.133023_bib0285","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2024.104871","article-title":"Advancing autonomous SLAM systems: integrating YOLO object detection and enhanced loop closure techniques for robust environment mapping","volume":"185","author":"Ul Islam","year":"2025","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.neucom.2026.133023_bib0290","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124474","article-title":"Advancing real-world visual SLAM: integrating adaptive segmentation with dynamic object detection for enhanced environmental perception","volume":"255","author":"Ul Islam","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133023_bib0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2024.102654","article-title":"Ard-SLAM: accurate and robust dynamic SLAM using dynamic object identification and improved multi-view geometrical approaches","volume":"82","author":"Ul Islam","year":"2024","journal-title":"Displays"},{"key":"10.1016\/j.neucom.2026.133023_bib0300","series-title":"2023 7th International Conference on Imaging, Signal Processing and Communications (ICISPC)","first-page":"22","article-title":"Dynamic object-aware SLAM: yolov8 integration and enhanced multi-view geometry for reliable mapping in dynamic environment","author":"Islam","year":"2023"},{"issue":"3","key":"10.1016\/j.neucom.2026.133023_bib0305","first-page":"254","article-title":"Fadm-SLAM: a fast and accurate dynamic intelligent motion SLAM for autonomous robot exploration involving movable objects","volume":"43","author":"Ul Islam","year":"2023","journal-title":"Robot. Intell. Autom."},{"issue":"1","key":"10.1016\/j.neucom.2026.133023_bib0310","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1002\/rob.22248","article-title":"Mvs-SLAM: enhanced multiview geometry for improved semantic RGBD SLAM in dynamic environment","volume":"41","author":"Islam","year":"2024","journal-title":"J. Field Robot."},{"key":"10.1016\/j.neucom.2026.133023_bib0315","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.111704","article-title":"SwinYOLOV7: robust ship detection in complex synthetic aperture radar images","volume":"160","author":"Yasir","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.neucom.2026.133023_bib0320","first-page":"1","article-title":"Semantic-independent dynamic SLAM based on geometric re-clustering and optical flow residuals","author":"Qi","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133023_bib0325","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"529","article-title":"Flownet3D: learning scene flow in 3D point clouds","author":"Liu","year":"2019"},{"key":"10.1016\/j.neucom.2026.133023_bib0330","series-title":"Computer Vision and Pattern Recognition (CVPR), 2019 IEEE International Conference on","article-title":"Hplflownet: hierarchical permutohedral lattice flownet for scene flow estimation on large-scale point clouds","author":"Gu","year":"2019"},{"key":"10.1016\/j.neucom.2026.133023_bib0335","series-title":"2007 IEEE 11th International Conference on Computer Vision","first-page":"1","article-title":"A variational method for scene flow estimation from stereo sequences","author":"Huguet","year":"2007"},{"key":"10.1016\/j.neucom.2026.133023_bib0340","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1377","article-title":"Piecewise rigid scene flow","author":"Vogel","year":"2013"},{"key":"10.1016\/j.neucom.2026.133023_bib0345","series-title":"Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001","article-title":"On 3D scene flow and structure estimation","volume":"vol. 2","author":"Zhang","year":"2001"},{"key":"10.1016\/j.neucom.2026.133023_bib0350","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3526","article-title":"Sphereflow: 6 DOF scene flow from RGB-D pairs","author":"Hornacek","year":"2014"},{"key":"10.1016\/j.neucom.2026.133023_bib0355","series-title":"2011 International Conference on Computer Vision","first-page":"2290","article-title":"Kinecting the dots: particle based scene flow from depth sensors","author":"Hadfield","year":"2011"},{"key":"10.1016\/j.neucom.2026.133023_bib0360","series-title":"ECCV","article-title":"Learning rigidity in dynamic scenes with a moving camera for 3D motion field estimation","author":"Lv","year":"2018"},{"key":"10.1016\/j.neucom.2026.133023_bib0365","series-title":"European Conference on Computer Vision","first-page":"567","article-title":"Dense semi-rigid scene flow estimation from RGBD images","author":"Quiroga","year":"2014"},{"key":"10.1016\/j.neucom.2026.133023_bib0370","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5538","article-title":"Effiscene: efficient per-pixel rigidity inference for unsupervised joint learning of optical flow, depth, camera pose and motion segmentation","author":"Jiao","year":"2021"},{"key":"10.1016\/j.neucom.2026.133023_bib0375","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2780","article-title":"Mono-sf: multi-view geometry meets single-view depth for monocular scene flow estimation of dynamic traffic scenes","author":"Brickwedde","year":"2019"},{"key":"10.1016\/j.neucom.2026.133023_bib0380","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2758","article-title":"Flownet: learning optical flow with convolutional networks","author":"Dosovitskiy","year":"2015"},{"key":"10.1016\/j.neucom.2026.133023_bib0385","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2462","article-title":"Flownet 2.0: evolution of optical flow estimation with deep networks","author":"Ilg","year":"2017"},{"key":"10.1016\/j.neucom.2026.133023_bib0390","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8934","article-title":"Pwc-net: CNNS for optical flow using pyramid, warping, and cost volume","author":"Sun","year":"2018"},{"key":"10.1016\/j.neucom.2026.133023_bib0395","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12240","article-title":"Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation","author":"Ranjan","year":"2019"},{"key":"10.1016\/j.neucom.2026.133023_bib0400","series-title":"International Conference on Computer Vision (ICCV)","article-title":"Slim: self-supervised lidar scene flow and motion segmentation","author":"Baur","year":"2021"},{"key":"10.1016\/j.neucom.2026.133023_bib0405","series-title":"European Conference on Computer Vision","first-page":"402","article-title":"Raft: recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0410","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Digging into self-supervised monocular depth estimation","author":"Godard","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0415","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Zhou","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2026.133023_bib0420","series-title":"2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","first-page":"1","article-title":"A survey of loss functions for semantic segmentation","author":"Jadon","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0425","series-title":"Conference on Computer Vision and Pattern Recognition","article-title":"Tangent space backpropagation for 3D transformation groups","author":"Teed","year":"2021"},{"key":"10.1016\/j.neucom.2026.133023_bib0430","author":"Cabon"},{"key":"10.1016\/j.neucom.2026.133023_bib0435","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","article-title":"Tartanair: a dataset to push the limits of visual SLAM","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133023_bib0440","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"19855","article-title":"Pointodyssey: a large-scale synthetic dataset for long-term point tracking","author":"Zheng","year":"2023"},{"key":"10.1016\/j.neucom.2026.133023_bib0445","author":"Kingma"},{"issue":"11","key":"10.1016\/j.neucom.2026.133023_bib0450","first-page":"120","article-title":"The opencv library","volume":"25","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s J.: Softw. Tools Prof. Program."},{"key":"10.1016\/j.neucom.2026.133023_bib0455","series-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"573","article-title":"A benchmark for the evaluation of RGB-D SLAM systems","author":"Sturm","year":"2012"},{"issue":"11","key":"10.1016\/j.neucom.2026.133023_bib0460","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: the kitti dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.neucom.2026.133023_bib0465","series-title":"IROS","first-page":"1680","article-title":"The tum VI benchmark for evaluating visual-inertial odometry","author":"Schubert","year":"2018"},{"issue":"10","key":"10.1016\/j.neucom.2026.133023_bib0470","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.1177\/0278364915620033","article-title":"The euroc micro aerial vehicle datasets","volume":"35","author":"Burri","year":"2016","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.neucom.2026.133023_bib0475","author":"Teed"},{"key":"10.1016\/j.neucom.2026.133023_bib0480","series-title":"Conference on Robot Learning","first-page":"1761","article-title":"Tartanvo: a generalizable learning-based VO","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133023_bib0485","author":"Campos"},{"key":"10.1016\/j.neucom.2026.133023_bib0490","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"822","article-title":"Deeptam: deep tracking and mapping","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neucom.2026.133023_bib0495","series-title":"2013 IEEE International Conference on Robotics and Automation","first-page":"3748","article-title":"Robust odometry estimation for RGB-D cameras","author":"Kerl","year":"2013"},{"issue":"5","key":"10.1016\/j.neucom.2026.133023_bib0500","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","article-title":"ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras","volume":"33","author":"Mur-Artal","year":"2017","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133023_bib0505","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1281","article-title":"D3VO: deep depth, deep pose and deep uncertainty for monocular visual odometry","author":"Yang","year":"2020"},{"issue":"2","key":"10.1016\/j.neucom.2026.133023_bib0510","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1109\/TRO.2016.2623335","article-title":"SVO: semidirect visual odometry for monocular and multicamera systems","volume":"33","author":"Forster","year":"2016","journal-title":"IEEE Trans. Robot."},{"issue":"4","key":"10.1016\/j.neucom.2026.133023_bib0515","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1109\/TRO.2020.2991614","article-title":"Direct sparse mapping","volume":"36","author":"Zubizarreta","year":"2020","journal-title":"IEEE Trans. Robot."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226004200?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226004200?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T06:19:55Z","timestamp":1775024395000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226004200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":103,"alternative-id":["S0925231226004200"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133023","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"D3FlowSLAM: Self-supervised dynamic SLAM with flow motion decomposition and DINO guidance","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133023","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133023"}}