{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:13:51Z","timestamp":1763644431902,"version":"3.40.3"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726262"},{"type":"electronic","value":"9783031726279"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72627-9_16","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"277-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["EgoPoser: Robust Real-Time Egocentric Pose Estimation from\u00a0Sparse and\u00a0Intermittent Observations Everywhere"],"prefix":"10.1007","author":[{"given":"Jiaxi","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Paul","family":"Streli","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Meier","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Holz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"16_CR1","unstructured":"CMU MoCap Dataset. (2004). http:\/\/mocap.cs.cmu.edu\/"},{"key":"16_CR2","unstructured":"RootMotion Final IK. (2018). https:\/\/assetstore.unity.com\/packages\/tools\/animation\/final-ik-14290"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Ahuja, K., Harrison, C., Goel, M., Xiao, R.: Mecap: whole-body digitization for low-cost vr\/ar headsets. In: Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology, pp. 453\u2013462 (2019)","DOI":"10.1145\/3332165.3347889"},{"issue":"2","key":"16_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3463499","volume":"5","author":"K Ahuja","year":"2021","unstructured":"Ahuja, K., Ofek, E., Gonzalez-Franco, M., Holz, C., Wilson, A.D.: Coolmoves: user motion accentuation in virtual reality. Proc. ACM Interact. Mobile Wearable Ubiquit. Technol. 5(2), 1\u201323 (2021)","journal-title":"Proc. ACM Interact. Mobile Wearable Ubiquit. Technol."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Ahuja, K., Shen, V., Fang, C.M., Riopelle, N., Kong, A., Harrison, C.: Controllerpose: inside-out body capture with VR controller cameras. In: CHI Conference on Human Factors in Computing Systems, pp. 1\u201313 (2022)","DOI":"10.1145\/3491102.3502105"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Akada, H., Wang, J., Shimada, S., Takahashi, M., Theobalt, C., Golyanik, V.: UnrealEgo: a new dataset for robust egocentric 3D human motion capture. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part VI, pp. 1\u201317. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_1","DOI":"10.1007\/978-3-031-20068-7_1"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Aliakbarian, S., Cameron, P., Bogo, F., Fitzgibbon, A., Cashman, T.J.: Flag: flow-based 3d avatar generation from sparse observations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13253\u201313262 (2022)","DOI":"10.1109\/CVPR52688.2022.01290"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Armani, R., Qian, C., Jiang, J., Holz, C.: Ultra inertial poser: scalable motion capture and tacking from sparse inertial sensors and ultra-wideband ranging. In: ACM SIGGRAPH 2024 Conference Papers (SIGGRAPH 2024). Association for Computing Machinery, New York (2024)","DOI":"10.1145\/3641519.3657465"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Bailly, G., M\u00fcller, J., Rohs, M., Wigdor, D., Kratz, S.: Shoesense: a new perspective on gestural interaction and wearable applications. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1239\u20131248 (2012)","DOI":"10.1145\/2207676.2208576"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Dittadi, A., Dziadzio, S., Cosker, D., Lundell, B., Cashman, T.J., Shotton, J.: Full-body motion from a single head-mounted device: generating SMPL poses from partial observations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11687\u201311697 (2021)","DOI":"10.1109\/ICCV48922.2021.01148"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Du, Y., Kips, R., Pumarola, A., Starke, S., Thabet, A., Sanakoyeu, A.: Avatars grow legs: generating smooth human motion from sparse tracking inputs with diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00054"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Fender, A., M\u00fcller, J.: Velt: a framework for multi RGB-D camera systems. In: Proceedings of the 2018 ACM International Conference on Interactive Surfaces and Spaces, pp. 73\u201383 (2018)","DOI":"10.1145\/3279778.3279794"},{"key":"16_CR14","unstructured":"Grauman, K., et\u00a0al.: Ego4d: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"16_CR15","unstructured":"Grauman, K., et\u00a0al.: Ego-exo4d: understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Guzov, V., Mir, A., Sattler, T., Pons-Moll, G.: Human poseitioning system (HPS): 3d human pose estimation and self-localization in large scenes from body-mounted sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4318\u20134329 (2021)","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Han, S., et al.: Megatrack: monochrome egocentric articulated hand-tracking for virtual reality. ACM Trans. Graph. 39(4), 87\u20131 (2020)","DOI":"10.1145\/3386569.3392452"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Han, S., et\u00a0al.: Umetrack: unified multi-view end-to-end hand tracking for VR. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3550469.3555378"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Y., Kaufmann, M., Aksan, E., Black, M.J., Hilliges, O., Pons-Moll, G.: Deep inertial poser: learning to reconstruct human pose from sparse inertial measurements in real time. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 37, 185:1\u2013185:15 (2018)","DOI":"10.1145\/3272127.3275108"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, J., Streli, P., Luo, X., Gebhardt, C., Holz, C.: MANIKIN: biomechanically accurate neural inverse kinematics for human motion estimation. In: European Conference on Computer Vision. Springer (2024)","DOI":"10.1007\/978-3-031-72627-9_8"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Jiang, J., et al.: AvatarPoser: articulated full-body pose tracking from\u00a0sparse motion sensing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part V, pp. 443\u2013460. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_26","DOI":"10.1007\/978-3-031-20065-6_26"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Ye, Y., Gopinath, D., Won, J., Winkler, A.W., Liu, C.K.: Transformer inertial poser: real-time human motion reconstruction from sparse IMUS with simultaneous terrain generation. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3550469.3555428"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Kang, T., Lee, K., Zhang, J., Lee, Y.: Ego3dpose: capturing 3d cues from binocular egocentric views. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618147"},{"key":"16_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Lee, S., Starke, S., Ye, Y., Won, J., Winkler, A.: Questenvsim: environment-aware simulated motion tracking from sparse sensors. arXiv preprint arXiv:2306.05666 (2023)","DOI":"10.1145\/3588432.3591504"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, K., Wu, J.: Ego-body pose estimation via ego-head pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17142\u201317151 (2023)","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Li, S., et al.: A mobile robot hand-arm teleoperation system by vision and IMU. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10900\u201310906. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9340738"},{"issue":"6","key":"16_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph."},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Ma, L., et\u00a0al.: Nymeria: a massive collection of multimodal egocentric daily motion in the wild. arXiv preprint arXiv:2406.09905 (2024)","DOI":"10.1007\/978-3-031-72691-0_25"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: International Conference on Computer Vision, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Mollyn, V., Arakawa, R., Goel, M., Harrison, C., Ahuja, K.: Imuposer: full-body pose estimation using IMUS in phones, watches, and earbuds. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, pp. 1\u201312 (2023)","DOI":"10.1145\/3544548.3581392"},{"key":"16_CR32","unstructured":"M\u00fcller, M., R\u00f6der, T., Clausen, M., Eberhardt, B., Kr\u00fcger, B., Weber, A.: Documentation mocap database hdm05. Tech. Rep. CG-2007-2, Universit\u00e4t Bonn (2007)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Parger, M., et al.: UNOC: understanding occlusion for embodied presence in virtual reality. IEEE Trans. Visual Comput. Graph. 28(12), 4240\u20134251 (2021)","DOI":"10.1109\/TVCG.2021.3085407"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Ponton, J.L., Yun, H., Aristidou, A., Andujar, C., Pelechano, N.: Sparseposer: real-time full-body motion reconstruction from sparse data. ACM Trans. Graph. 43(1), 1\u201314 (2023)","DOI":"10.1145\/3625264"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Rhodin, H., et al.: Egocap: egocentric marker-less motion capture with two fisheye cameras. ACM Trans. Graph. 35(6), 1\u201311 (2016)","DOI":"10.1145\/2980179.2980235"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Streli, P., Armani, R., Cheng, Y.F., Holz, C.: HOOV: hand out-of-view tracking for proprioceptive interaction using inertial sensing. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, pp. 1\u201316 (2023)","DOI":"10.1145\/3544548.3581468"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Troje, N.F.: Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. J. Vision 2(5), 2 (2002)","DOI":"10.1167\/2.5.2"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Van\u00a0Wouwe, T., Lee, S., Falisse, A., Delp, S., Liu, C.K.: Diffusionposer: real-time human motion reconstruction from arbitrary sparse sensors using autoregressive diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2513\u20132523 (2024)","DOI":"10.1109\/CVPR52733.2024.00243"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Von\u00a0Marcard, T., Rosenhahn, B., Black, M.J., Pons-Moll, G.: Sparse inertial poser: automatic 3d human pose estimation from sparse IMUS. In: Computer Graphics Forum, vol.\u00a036, pp. 349\u2013360. Wiley Online Library (2017)","DOI":"10.1111\/cgf.13131"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, L., Xu, W., Sarkar, K., Theobalt, C.: Estimating egocentric 3D human pose in global space. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11500\u201311509 (2021)","DOI":"10.1109\/ICCV48922.2021.01130"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Winkler, A., Won, J., Ye, Y.: Questsim: human motion tracking from sparse sensors with simulated avatars. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3550469.3555411"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Wu, E., Yuan, Y., Yeo, H.S., Quigley, A., Koike, H., Kitani, K.M.: Back-hand-pose: 3D hand pose estimation for a wrist-worn camera via dorsum deformation network. In: Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology, pp. 1147\u20131160 (2020)","DOI":"10.1145\/3379337.3415897"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Xie, X., Bhatnagar, B.L., Pons-Moll, G.: Visibility aware human-object interaction tracking from single RGB camera. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4757\u20134768 (2023)","DOI":"10.1109\/CVPR52729.2023.00461"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Yang, D., Kim, D., Lee, S.H.: Lobstr: real-time lower-body pose prediction from sparse upper-body tracking signals. In: Computer Graphics Forum, vol.\u00a040, pp. 265\u2013275. Wiley Online Library (2021)","DOI":"10.1111\/cgf.142631"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Yi, X., et al.: Egolocate: real-time motion capture, localization, and mapping with sparse body-mounted sensors. ACM Trans. Graph. 42(4), 1\u201317 (2023)","DOI":"10.1145\/3592099"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Yi, X., et al.: Physical inertial poser (PIP): physics-aware real-time human motion tracking from sparse inertial sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13167\u201313178 (2022)","DOI":"10.1109\/CVPR52688.2022.01282"},{"issue":"4","key":"16_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459786","volume":"40","author":"X Yi","year":"2021","unstructured":"Yi, X., Zhou, Y., Xu, F.: Transpose: real-time 3d human translation and pose estimation with six inertial sensors. ACM Trans. Graph. 40(4), 1\u201313 (2021)","journal-title":"ACM Trans. Graph."},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Yi, X., Zhou, Y., Xu, F.: Physical non-inertial poser (PNP): modeling non-inertial effects in sparse-inertial human motion capture. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657436"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Wei, S.E., Simon, T., Kitani, K., Saragih, J.: Simpoe: simulated character control for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7159\u20137169 (2021)","DOI":"10.1109\/CVPR46437.2021.00708"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, D., Wei, Z., Mahmud, J., Frahm, J.M.: Egoglass: egocentric-view human pose estimation from an eyeglass frame. In: 2021 International Conference on 3D Vision (3DV), pp. 32\u201341. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00014"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Zheng, X., Su, Z., Wen, C., Xue, Z., Jin, X.: Realistic full-body tracking from sparse observations via joint-level modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14678\u201314688 (2023)","DOI":"10.1109\/ICCV51070.2023.01349"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72627-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:44:49Z","timestamp":1732920289000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}