{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:46:58Z","timestamp":1792003618714,"version":"4.4.0"},"reference-count":97,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"119","license":[{"start":{"date-parts":[[2027,10,14]],"date-time":"2027-10-14T00:00:00Z","timestamp":1823472000000},"content-version":"vor","delay-in-days":365,"URL":"https:\/\/www.science.org\/content\/page\/science-licenses-journal-article-reuse"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2145164"],"award-info":[{"award-number":["IIS-2145164"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2212519"],"award-info":[{"award-number":["CCF-2212519"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EEC-1941529"],"award-info":[{"award-number":["EEC-1941529"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DSO Laboratories"}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2026,10,14]]},"abstract":"<jats:p>\n                    This paper develops a mathematical argument and algorithms for building representations of data from event-based cameras that we call Fast Feature Field (F\n                    <jats:sup>3<\/jats:sup>\n                    ). We learned this representation by predicting future events from past events and show that it preserves scene structure and motion information. F\n                    <jats:sup>3<\/jats:sup>\n                    exploits the sparsity of event data and is robust to noise and variations in event rates. It can be computed efficiently using ideas from multiresolution hash encoding and deep sets, achieving 120 hertz at high-definition (HD) resolution and 440 hertz at video graphics array (VGA) resolution. F\n                    <jats:sup>3<\/jats:sup>\n                    represents events in a contiguous spatiotemporal volume as a multichannel image, enabling a range of downstream tasks. We obtained state-of-the-art performance on optical flow estimation, semantic segmentation, and monocular metric depth estimation, on data from three robotic platforms (a car, a quadruped robot, and a flying platform) and across different lighting conditions (daytime and nighttime), environments (indoors, outdoors, urban, and off-road), and dynamic vision sensors (resolutions and event rates). Our implementations can predict these tasks at 25 to 75 hertz at HD resolution.\n                  <\/jats:p>","DOI":"10.1126\/scirobotics.aec8218","type":"journal-article","created":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:59:57Z","timestamp":1792000797000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Fast Feature Field (F\n                    <sup>3<\/sup>\n                    ): A general predictive representation of events for robot perception"],"prefix":"10.1126","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2020-123X","authenticated-orcid":true,"given":"Richeek","family":"Das","sequence":"first","affiliation":[{"name":"Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0498-0758","authenticated-orcid":true,"given":"Kostas","family":"Daniilidis","sequence":"additional","affiliation":[{"name":"Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4590-1956","authenticated-orcid":true,"given":"Pratik","family":"Chaudhari","sequence":"additional","affiliation":[{"name":"Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90024-X"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2006.05.056"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800793"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"K. Chaney F. Cladera Z. Wang A. Bisulco M. A. Hsieh C. Korpela V. Kumar C. J. Taylor K. Daniilidis \u201cM3ed: Multi-robot multi-sensor multi-environment event dataset\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2023) pp. 4016\u20134023.","DOI":"10.1109\/CVPRW59228.2023.00419"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"D. Marr Vision: A Computational Investigation into the Human Representation and Processing of Visual Information (MIT Press 2010).","DOI":"10.7551\/mitpress\/9780262514620.001.0001"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/81.3.425"},{"key":"e_1_3_2_9_2","unstructured":"S. Mallat A Wavelet Tour of Signal Processing: The Sparse Way (Elsevier 2008)."},{"key":"e_1_3_2_10_2","first-page":"1317","article-title":"Ideal denoising in an orthonormal basis chosen from a library of bases","volume":"319","author":"Donoho D. L.","year":"1994","unstructured":"D. L. Donoho, I. M. Johnstone, Ideal denoising in an orthonormal basis chosen from a library of bases. C. R. Acad. Sci., Ser. I, Math. 319, 1317\u20131322 (1994).","journal-title":"C. R. Acad. Sci., Ser. I, Math."},{"key":"e_1_3_2_11_2","unstructured":"M. Zaheer S. Kottur S. Ravanbakhsh B. Poczos R. R. Salakhutdinov A. J. Smola \u201cDeep sets\u201d in Advances in Neural Information Processing Systems 30 U. von Luxburg S. Bengio R. Fergus R. Garnett I. Guyon H. Wallach S. V. N. Vishwanathan Eds. (Curran Associates 2017) pp. 3391\u20133401."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.230"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"A. Z. Zhu L. Yuan K. Chaney K. Daniilidis \u201cUnsupervised event-based learning of optical flow depth and egomotion\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2019) pp. 989\u2013997.","DOI":"10.1109\/CVPR.2019.00108"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"A. I. Maqueda A. Loquercio G. Gallego N. Garcia D. Scaramuzza \u201cEvent-based vision meets deep learning on steering prediction for self-driving cars\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE 2018) pp. 5419\u20135427.","DOI":"10.1109\/CVPR.2018.00568"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3135635"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3548523"},{"key":"e_1_3_2_18_2","unstructured":"J. Mukhoti V. Kulharia A. Sanyal S. Golodetz P. Torr P. Dokania \u201cCalibrating deep neural networks using focal loss\u201d in Advances in Neural Information Processing Systems 33 H. Larochelle M. Ranzato R. Hadsell M.F. Balcan H. Lin Eds. (Curran Associates 2020) pp. 15288\u201315299."},{"key":"e_1_3_2_19_2","unstructured":"E. Xie W. Wang Z. Yu A. Anandkumar J. M. Alvarez P. Luo \u201cSegFormer: Simple and efficient design for semantic segmentation with transformers\u201d in Advances in Neural Information Processing Systems 34 M. Ranzato A. Beygelzimer Y. Dauphin P. S. Liang J. Wortman Vaughan Eds. (Curran Associates 2021) pp. 12077\u201312090."},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"M. Cordts M. Omran S. Ramos T. Rehfeld M. Enzweiler R. Benenson U. Franke S. Roth B. Schiele \u201cThe cityscapes dataset for semantic urban scene understanding\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2016) pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Z. Sun N. Messikommer D. Gehrig D. Scaramuzza \u201cESS: Learning event-based semantic segmentation from still Images\u201d in Computer Vision \u2013 ECCV 2022: 17th European Conference Tel Aviv Israel October 23\u201327 2022 Proceedings Part XXXIV S. Avidan G. Brostow M. Ciss\u00e9 G. M. Farinella T. Hassner Eds. (Springer 2022) pp. 341\u2013357.","DOI":"10.1007\/978-3-031-19830-4_20"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"I. Alonso A. C. Murillo \u201cEV-SegNet: Semantic segmentation for event-based cameras\u201d in IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE 2019) pp. 1624\u20131633.","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963386"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"W. Wang J. Dai Z. Chen Z. Huang Z. Li X. Zhu X. Hu T. Lu L. Lu H. Li X. Wang Y. Qiao \u201cInternimage: Exploring large-scale vision foundation models with deformable convolutions\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2023) pp. 14408\u201314419.","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"e_1_3_2_25_2","unstructured":"A. Tao K. Sapra B. Catanzaro Hierarchical multi-scale attention for semantic segmentation. arXiv:2005.10821 [cs.CV] (2020)."},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Y. Ma S. Soatto J. Ko\u0161eck\u00e1 S. S. Sastry An Invitation to 3-D Vision: From Images to Geometric Models vol. 26 of Interdisciplinary Applied Mathematics (Springer 2004).","DOI":"10.1007\/978-0-387-21779-6"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3396116"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"A. Z. Zhu L. Yuan K. Chaney K. Daniilidis \u201cLive demonstration: Unsupervised event-based learning of optical flow depth and egomotion\u201d in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE 2019) p. 1694.","DOI":"10.1109\/CVPRW.2019.00216"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22145190"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"M. Gehrig M. Millh\u00e4usler D. Gehrig D. Scaramuzza \u201cE-RAFT: Dense optical flow from event cameras\u201d in 2021 International Conference on 3D Vision (3DV) (IEEE 2021) pp. 197\u2013206.","DOI":"10.1109\/3DV53792.2021.00030"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"A. Zhu L. Yuan K. Chaney K. Daniilidis \u201cEV-FlowNet: Self-supervised optical flow estimation for event-based cameras\u201d in Proceedings of Robotics: Science and Systems H. Kress-Gazit S. Srinivasa T. Howard N. Atanasov Eds. (RSS Foundation 2018); https:\/\/doi.org\/10.15607\/RSS.2018.XIV.062.","DOI":"10.15607\/RSS.2018.XIV.062"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0644-x"},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","unstructured":"D. Sun S. Roth M. J. Black \u201cSecrets of optical flow estimation and their principles\u201d in 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE 2010) pp. 2432\u20132439.","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0390-2"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"F. Hamann Z. Wang I. Asmanis K. Chaney G. Gallego K. Daniilidis \u201cMotion-prior contrast maximization for dense continuous-time motion estimation\u201d in Computer Vision \u2013 ECCV 2024 18th European Conference A. Leonardis E. Ricci S. Roth O. Russakovsky T. Sattler G. Varol Eds. (Springer 2024) pp. 18\u201337.","DOI":"10.1007\/978-3-031-72646-0_2"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"H. You Y. Cao W. Yuan F. Wang N. Qiao Y. Li Vector-symbolic architecture for event-based optical flow. arXiv:2405.08300 [cs.CV] (2025).","DOI":"10.1007\/s11263-026-02951-8"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"A. Sironi M. Brambilla N. Bourdis X. Lagorce R. Benosman \u201cHATS: Histograms of averaged time surfaces for robust event-based object classification\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE 2018) pp. 1731\u20131740.","DOI":"10.1109\/CVPR.2018.00186"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2574707"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"S. Guo F. Hamann G. Gallego \u201cUnsupervised joint learning of optical flow and intensity with event cameras\u201d in 2025 IEEE\/CVF International Conference on Computer Vision (ICCV) (IEEE 2025) pp. 7980\u20137989.","DOI":"10.1109\/ICCV51701.2025.00748"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Z. Teed J. Deng \u201cRAFT: Recurrent all-pairs field transforms for optical flow\u201d in Computer Vision \u2013 ECCV 2020 16th European Conference (Springer 2020) pp. 402\u2013419.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"L. Yang B. Kang Z. Huang Z. Zhao X. Xu J. Feng H. Zhao Depth Anything V2. arXiv:2406.09414 [cs.CV] (2024).","DOI":"10.52202\/079017-0688"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"e_1_3_2_43_2","unstructured":"D. Eigen C. Puhrsch R. Fergus \u201cDepth map prediction from a single image using a multi-scale deep network\u201d in Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2 NIPS\u201914 Z. Ghahramani M. Welling C. Cortes N. D. Lawrence K. Q. Weinberger Eds. (MIT Press 2014) pp. 2366\u20132374."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3378742"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"J. Hidalgo-Carrio D. Gehrig D. Scaramuzza \u201cLearning monocular dense depth from events\u201d in 2020 International Conference on 3D Vision (3DV) (IEEE 2020) pp. 534\u2013542.","DOI":"10.1109\/3DV50981.2020.00063"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"L. Wang Y. Chae K.-J. Yoon \u201cDual transfer learning for event-based end-task prediction via pluggable event to image translation\u201d in 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (IEEE 2021) pp. 2135\u20132145.","DOI":"10.1109\/ICCV48922.2021.00214"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060707"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311336"},{"key":"e_1_3_2_49_2","unstructured":"L. Burner A. Mitrokhin C. Ferm\u00fcller Y. Aloimonos EVIMO2: An event camera dataset for motion segmentation optical flow structure from motion and visual inertial odometry in indoor scenes with monocular or stereo algorithms. arXiv:2205.03467 [cs.CV] (2022)."},{"key":"e_1_3_2_50_2","first-page":"1947","article-title":"Emergence of invariance and disentanglement in deep representations","volume":"19","author":"Achille A.","year":"2018","unstructured":"A. Achille, S. Soatto, Emergence of invariance and disentanglement in deep representations. J. Mach. Learn. Res. 19, 1947\u20131980 (2018).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_51_2","unstructured":"T. Cohen \u201cEquivariant convolutional networks \u201d thesis University of Amsterdam Amsterdam Netherlands (2021)."},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Y. Xu J. Lei K. Daniilidis \u201cSE(3) equivariant convolution and transformer in ray space\u201d in Proceedings of the 37th International Conference on Neural Information Processing Systems A. Oh T. Naumann A. Globerson K. Saenko M. Hardt S. Levine Eds. vol. 36 (Curran Associates Inc. 2023) pp. 2463\u20132510.","DOI":"10.52202\/075280-0114"},{"key":"e_1_3_2_53_2","doi-asserted-by":"crossref","unstructured":"M. Assran Q. Duval I. Misra P. Bojanowski P. Vincent M. Rabbat Y. LeCun N. Ballas Self-supervised learning from images with a joint-embedding predictive architecture. arXiv:2301.08243 [cs.CV] (2023).","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"e_1_3_2_54_2","unstructured":"M. Oquab T. Darcet T. Moutakanni H. V. Vo M. Szafraniec V. Khalidov P. Fernandez D. Haziza F. Massa A. El-Nouby M. Assran N. Ballas W. Galuba R. Howes P.-Y. Huang S.-W. Li I. Misra M. Rabbat V. Sharma G. Synnaeve H. Xu H. J\u00e9gou J. Mairal P. Labatut A. Joulin P. Bojanowski DINOv2: Learning robust visual features without supervision. arXiv:2304.07193 [cs.CV] (2023)."},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"K. He X. Chen S. Xie Y. Li P. Doll\u00e1r R. Girshick \u201cMasked autoencoders are scalable vision learners\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2022) pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_56_2","unstructured":"M. Assran A. Bardes D. Fan Q. Garrido R. Howes M. Komeili M. Muckley A. Rizvi C. Roberts K. Sinha A. Zholus S. Arnaud A. Gejji A. Martin F. R. Hogan D. Dugas P. Bojanowski V. Khalidov P. Labatut F. Massa M. Szafraniec K. Krishnakumar Y. Li X. Ma S. Chandar F. Meier Y. LeCun M. Rabbat N. Ballas V-JEPA 2: Self-supervised video models enable understanding prediction and planning. arXiv:2506.09985 [cs.AI] (2025)."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","unstructured":"S. Zhu Z. Tang M. Yang E. Learned-Miller D. Kim \u201cEvent camera-based visual odometry for dynamic motion tracking of a legged robot using adaptive time surface\u201d in 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2023) pp. 3475\u20133482.","DOI":"10.1109\/IROS55552.2023.10342048"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3565150"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01410-2"},{"key":"e_1_3_2_61_2","unstructured":"X. Zheng Y. Liu Y. Lu T. Hua T. Pan W. Zhang D. Tao L. Wang Deep learning for event-based vision: A comprehensive survey and benchmarks. arXiv:2302.08890 [cs.CV] (2024)."},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3586559"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129899"},{"key":"e_1_3_2_64_2","doi-asserted-by":"crossref","unstructured":"Y. Nam M. Mostafavi K.-J. Yoon J. Choi \u201cStereo depth from events cameras: Concentrate and focus on the future\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2022) pp. 6114\u20136123.","DOI":"10.1109\/CVPR52688.2022.00602"},{"key":"e_1_3_2_65_2","unstructured":"M. Liu T. Delbruck \u201cAdaptive time-slice block-matching optical flow algorithm for dynamic vision sensors\u201d in 29th British Machine Vision Conference (British Machine Vision Association 2018); https:\/\/bmva-archive.org.uk\/bmvc\/2018\/contents\/papers\/0280.pdf."},{"key":"e_1_3_2_66_2","doi-asserted-by":"crossref","unstructured":"A. Zihao Zhu L. Yuan K. Chaney K. Daniilidis \u201cUnsupervised event-based optical flow using motion compensation\u201d in Computer Vision \u2013 ECCV 2018 15th European Conference V. Ferrari M. Hebert C. Sminchisescu Y. Weiss Eds. (Springer 2018) https:\/\/doi.org\/10.1007\/978-3-030-11024-6_54.","DOI":"10.1007\/978-3-030-11024-6_54"},{"key":"e_1_3_2_67_2","doi-asserted-by":"crossref","unstructured":"S. Schaefer D. Gehrig D. Scaramuzza \u201cAegnn: Asynchronous event-based graph neural networks\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2022) pp. 12371\u201312381.","DOI":"10.1109\/CVPR52688.2022.01205"},{"key":"e_1_3_2_68_2","unstructured":"W. Fang P. Panda Event2Vec: Processing neuromorphic events directly by representations in vector space. arXiv:2504.15371 [cs.CV] (2026)."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2893427"},{"key":"e_1_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Z. Huang L. Sun C. Zhao S. Li S. Su \u201cEventpoint: Self-supervised interest point detection and description for event-based camera\u201d in Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (IEEE 2023) pp. 5396\u20135405.","DOI":"10.1109\/WACV56688.2023.00536"},{"key":"e_1_3_2_71_2","doi-asserted-by":"crossref","unstructured":"N. Zubi\u0107 D. Gehrig M. Gehrig D. Scaramuzza \u201cFrom chaos comes order: Ordering event representations for object recognition and detection\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (IEEE 2023) pp. 12846\u201312856.","DOI":"10.1109\/ICCV51070.2023.01180"},{"key":"e_1_3_2_72_2","doi-asserted-by":"crossref","unstructured":"H. M. So G. Wetzstein \u201cNeural ganglion sensors: Learning task-specific event cameras inspired by the neural circuit of the human retina\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops (IEEE 2025) pp. 4675\u20134685.","DOI":"10.1109\/ICCVW69036.2025.00485"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaz9712"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2885575"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi0591"},{"key":"e_1_3_2_76_2","doi-asserted-by":"crossref","unstructured":"E. Mueggler B. Huber D. Scaramuzza \u201cEvent-based 6-DOF pose tracking for high-speed maneuvers\u201d in 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2014) pp. 2761\u20132768.","DOI":"10.1109\/IROS.2014.6942940"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188400"},{"key":"e_1_3_2_78_2","doi-asserted-by":"crossref","unstructured":"A. Mitrokhin C. Ferm\u00fcller C. Parameshwara Y. Aloimonos \u201cEvent-based moving object detection and tracking\u201d in 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2018) pp. 1\u20139.","DOI":"10.1109\/IROS.2018.8593805"},{"key":"e_1_3_2_79_2","doi-asserted-by":"crossref","unstructured":"N. J. Sanket C. M. Parameshwara C. D. Singh A. V. Kuruttukulam C. Ferm\u00fcller D. Scaramuzza Y. Aloimonos \u201cEvdodgenet: Deep dynamic obstacle dodging with event cameras\u201d in 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2020) pp. 10651\u201310657.","DOI":"10.1109\/ICRA40945.2020.9196877"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3067593"},{"key":"e_1_3_2_81_2","unstructured":"S. J. Carey A. Lopich D. R. Barr B. Wang P. Dudek \u201cA 100 000 fps vision sensor with embedded 535GOPS\/W 256 \u00d7 256 SIMD processor array\u201d in 2013 Symposium on VLSI Circuits (IEEE 2013) pp. C182\u2013C183."},{"key":"e_1_3_2_82_2","doi-asserted-by":"crossref","unstructured":"J. Cao J. Xing N. Messikommer D. Scaramuzza \u201cGenerative event pretraining with foundation model alignment\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings (Computer Vision Foundation 2026) pp. 3189\u20133199.","DOI":"10.1109\/CVPRF71909.2026.00310"},{"key":"e_1_3_2_83_2","doi-asserted-by":"crossref","unstructured":"S. Woo S. Debnath R. Hu X. Chen Z. Liu I. S. Kweon S. Xie \u201cConvNeXt V2: Co-designing and scaling ConvNets with masked autoencoders\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2023) pp. 16133\u201316142.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"e_1_3_2_84_2","doi-asserted-by":"crossref","unstructured":"C. Choy J. Gwak S. Savarese \u201c4D spatio-temporal ConvNets: Minkowski convolutional neural networks\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE 2019) pp. 3075\u20133084.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_2_85_2","doi-asserted-by":"crossref","unstructured":"H. Tang S. Yang Z. Liu K. Hong Z. Yu X. Li G. Dai Y. Wang S. Han \u201cTorchSparse++: Efficient training and inference framework for sparse convolution on GPUs\u201d in Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture MICRO \u201823 (Association for Computing Machinery 2023) pp. 225\u2013239.","DOI":"10.1145\/3613424.3614303"},{"key":"e_1_3_2_86_2","doi-asserted-by":"crossref","unstructured":"J. Ansel E. Yang H. He N. E. A. Gimelshein \u201cPyTorch 2: Faster machine learning through dynamic Python bytecode transformation and graph compilation\u201d in Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems Volume 2 (Association for Computing Machinery 2024) pp. 929\u2013947.","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_2_87_2","unstructured":"J. L. Ba J. R. Kiros G. E. Hinton Layer normalization. arXiv:1607.06450 [stat.ML] (2016)."},{"key":"e_1_3_2_88_2","doi-asserted-by":"crossref","unstructured":"O. Ronneberger P. Fischer T. Brox \u201cU-Net: Convolutional networks for biomedical image segmentation\u201d in Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention N. Navab J. Hornegger W. M. Wells A. F. Frangi Eds. (Springer 2015) pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_89_2","unstructured":"C. Guo G. Pleiss Y. Sun K. Q. Weinberger \u201cOn calibration of modern neural networks\u201d in Proceedings of the 34th International Conference on Machine Learning - Volume 70 D. Precup Y. W. Teh Eds. (JMLR.org 2017) pp. 1321\u20131330."},{"key":"e_1_3_2_90_2","doi-asserted-by":"crossref","unstructured":"A. Z. Zhu L. Yuan K. Chaney K. Daniilidis \u201cUnsupervised event-based learning of optical flow depth and egomotion\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2019) pp. 989\u2013997.","DOI":"10.1109\/CVPR.2019.00108"},{"key":"e_1_3_2_91_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3365160","article-title":"EV-MGRFlowNet: Motion-guided recurrent network for unsupervised event-based optical flow with hybrid motion-compensation loss","volume":"73","author":"Zhuang H.","year":"2024","unstructured":"H. Zhuang, Z. Fang, X. Huang, K. Hou, D. Kong, C. Hu, EV-MGRFlowNet: Motion-guided recurrent network for unsupervised event-based optical flow with hybrid motion-compensation loss. IEEE Trans. Instrum. Meas. 73, 1\u201315 (2024).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"e_1_3_2_92_2","doi-asserted-by":"crossref","unstructured":"F. Paredes-Vall\u00e9s K. Y. W. Scheper C. De Wagter G. C. H. E. de Croon \u201cTaming contrast maximization for learning sequential low-latency event-based optical flow\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (IEEE 2023) pp. 9661\u20139671.","DOI":"10.1109\/ICCV51070.2023.00889"},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152830"},{"key":"e_1_3_2_94_2","doi-asserted-by":"crossref","unstructured":"J. J. Hagenaars Y. Wu F. Paredes-Vall\u00e9s S. Stroobants G. C. de Croon \u201cOn-device self-supervised learning of low-latency monocular depth from only events\u201d in 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2025) pp. 17114\u201317123.","DOI":"10.1109\/CVPR52734.2025.01595"},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1166"},{"key":"e_1_3_2_96_2","doi-asserted-by":"crossref","unstructured":"W. Wang D. Zhu X. Wang Y. Hu Y. Qiu C. Wang Y. Hu A. Kapoor S. Scherer \u201cTartanAir: A dataset to push the limits of visual SLAM\u201d in 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2020) pp. 4909\u20134916.","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"e_1_3_2_97_2","unstructured":"R. Das P. Chaudhari Neurosim: A fast simulator for neuromorphic robot perception. arXiv:2602.15018 [cs.RO] (2026)."},{"key":"e_1_3_2_98_2","doi-asserted-by":"crossref","unstructured":"Y. Wu F. Paredes-Vall\u00e9s G. C. H. E. de Croon \u201cLightweight event-based optical flow estimation via iterative deblurring\u201d in 2024 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2024) pp. 14708\u201314715.","DOI":"10.1109\/ICRA57147.2024.10610353"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.aec8218","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.aec8218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:00:27Z","timestamp":1792000827000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.aec8218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,14]]},"references-count":97,"journal-issue":{"issue":"119","published-print":{"date-parts":[[2026,10,14]]}},"alternative-id":["10.1126\/scirobotics.aec8218"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.aec8218","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,14]]},"assertion":[{"value":"2025-10-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eaec8218"}}