{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:22:14Z","timestamp":1760955734863,"version":"3.41.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319667089"},{"type":"electronic","value":"9783319667096"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-66709-6_28","type":"book-chapter","created":{"date-parts":[[2017,8,14]],"date-time":"2017-08-14T04:13:01Z","timestamp":1502683981000},"page":"347-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Optical Flow-Based 3D Human Motion Estimation from Monocular Video"],"prefix":"10.1007","author":[{"given":"Thiemo","family":"Alldieck","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Kassubeck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Wandt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bodo","family":"Rosenhahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Magnor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,15]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1446\u20131455 (2015)","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: shape completion and animation of people. In: ACM Transactions on Graphics (TOG), vol. 24, pp. 408\u2013416. ACM (2005)","DOI":"10.1145\/1186822.1073207"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"B\u0103lan, A.O., Black, M.J., Haussecker, H., Sigal, L.: Shining a light on human pose: on shadows, shading and the estimation of pose and shape. In: IEEE International Conference on Computer Vision, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4409005"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"B\u0103lan, A.O., Sigal, L., Black, M.J., Davis, J.E., Haussecker, H.W.: Detailed human shape and pose from images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383340"},{"key":"28_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). doi: 10.1007\/978-3-319-46454-1_34"},{"key":"28_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/11744047_8","volume-title":"Computer Vision \u2013 ECCV 2006","author":"T Brox","year":"2006","unstructured":"Brox, T., Rosenhahn, B., Cremers, D., Seidel, H.-P.: High accuracy optical flow serves 3-D pose tracking: exploiting contour and flow based constraints. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 98\u2013111. Springer, Heidelberg (2006). doi: 10.1007\/11744047_8"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Carranza, J., Theobalt, C., Magnor, M.A., Seidel, H.P.: Free-viewpoint video of human actors. In: ACM transactions on graphics (TOG), vol. 22, pp. 569\u2013577. ACM (2003)","DOI":"10.1145\/1201775.882309"},{"key":"28_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-642-15558-1_22","volume-title":"Computer Vision \u2013 ECCV 2010","author":"Y Chen","year":"2010","unstructured":"Chen, Y., Kim, T.-K., Cipolla, R.: Inferring 3D shapes and deformations from single views. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6313, pp. 300\u2013313. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15558-1_22"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: IEEE International Conference on Computer Vision, pp. 726\u2013733. IEEE (2003)","DOI":"10.1109\/ICCV.2003.1238420"},{"issue":"3","key":"28_CR10","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TPAMI.2016.2557779","volume":"39","author":"A Elhayek","year":"2017","unstructured":"Elhayek, A., de Aguiar, E., Jain, A., Thompson, J., Pishchulin, L., Andriluka, M., Bregler, C., Schiele, B., Theobalt, C.: MARCOnI\u2014ConvNet-based marker-less motion capture in outdoor and indoor scenes. IEEE Trans. Pattern Anal. Mach. Intell. 39(3), 501\u2013514 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1007\/3-540-47969-4_32","volume-title":"Computer Vision \u2014 ECCV 2002","author":"R Fablet","year":"2002","unstructured":"Fablet, R., Black, M.J.: Automatic detection and tracking of human motion with a view-based representation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 476\u2013491. Springer, Heidelberg (2002). doi: 10.1007\/3-540-47969-4_32"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Hu, H., Shi, J.: Pose from flow and flow from pose. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2059\u20132066 (2013)","DOI":"10.1109\/CVPR.2013.268"},{"key":"28_CR13","volume-title":"The Perception of the Visual World","author":"JJ Gibson","year":"1950","unstructured":"Gibson, J.J.: The Perception of the Visual World. Houghton Mifflin, Boston (1950)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Guan, P., Weiss, A., B\u0103lan, A.O., Black, M.J.: Estimating human shape and pose from a single image. In: International Conference on Computer Vision, pp. 1381\u20131388. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459300"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Hasler, N., Ackermann, H., Rosenhahn, B., Thormahlen, T., Seidel, H.P.: Multilinear pose and body shape estimation of dressed subjects from image sets. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1823\u20131830. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539853"},{"key":"28_CR16","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1111\/j.1467-8659.2009.01373.x","volume":"28","author":"N Hasler","year":"2009","unstructured":"Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. Comput. Graph. Forum. 28, 337\u2013346 (2009)","journal-title":"Comput. Graph. Forum."},{"issue":"1\u20133","key":"28_CR17","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BK Horn","year":"1981","unstructured":"Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1\u20133), 185\u2013203 (1981)","journal-title":"Artif. Intell."},{"issue":"6","key":"28_CR18","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1145\/1882261.1866174","volume":"29","author":"A Jain","year":"2010","unstructured":"Jain, A., Thorm\u00e4hlen, T., Seidel, H.P., Theobalt, C.: MovieReshape: tracking and reshaping of humans in videos. ACM Trans. Graph. (TOG) 29(6), 148 (2010)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-319-10584-0_11","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MM Loper","year":"2014","unstructured":"Loper, M.M., Black, M.J.: OpenDR: an approximate differentiable renderer. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 154\u2013169. Springer, Cham (2014). doi: 10.1007\/978-3-319-10584-0_11"},{"issue":"6","key":"28_CR20","doi-asserted-by":"crossref","first-page":"248:1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"MM Loper","year":"2015","unstructured":"Loper, M.M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6), 248:1\u2013248:16 (2015)","journal-title":"ACM Trans. Graph."},{"volume-title":"Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality","year":"2015","key":"28_CR21","unstructured":"Magnor, M.A., Grau, O., Sorkine-Hornung, O., Theobalt, C. (eds.): Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality. CRC Press, Boca Raton (2015)"},{"issue":"2","key":"28_CR22","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","volume":"104","author":"TB Moeslund","year":"2006","unstructured":"Moeslund, T.B., Hilton, A., Kr\u00fcger, V.: A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Underst. 104(2), 90\u2013126 (2006)","journal-title":"Comput. Vis. Image Underst."},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Oliveira, G.L., Valada, A., Bollen, C., Burgard, W., Brox, T.: Deep learning for human part discovery in images. In: IEEE International Conference on Robotics and Automation (2016)","DOI":"10.1109\/ICRA.2016.7487304"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B.: Deepcut: Joint subset partition and labeling for multi person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.533"},{"key":"28_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1007\/978-3-642-33765-9_41","volume-title":"Computer Vision \u2013 ECCV 2012","author":"V Ramakrishna","year":"2012","unstructured":"Ramakrishna, V., Kanade, T., Sheikh, Y.: Reconstructing 3D human pose from 2D image landmarks. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 573\u2013586. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-33765-9_41"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Rehan, A., Zaheer, A., Akhter, I., Saeed, A., Mahmood, B., Usmani, M., Khan, S.: NRSfM using local rigidity. In: Winter Conference on Applications of Computer Vision, pp. 69\u201374. IEEE, Steamboat Springs, March 2014","DOI":"10.1109\/WACV.2014.6836116"},{"key":"28_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/978-3-319-46454-1_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Rhodin","year":"2016","unstructured":"Rhodin, H., Robertini, N., Casas, D., Richardt, C., Seidel, H.-P., Theobalt, C.: General automatic human shape and motion capture using volumetric contour cues. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 509\u2013526. Springer, Cham (2016). doi: 10.1007\/978-3-319-46454-1_31"},{"issue":"1","key":"28_CR28","doi-asserted-by":"crossref","first-page":"6:1","DOI":"10.1145\/2634212","volume":"34","author":"L Rogge","year":"2014","unstructured":"Rogge, L., Klose, F., Stengel, M., Eisemann, M., Magnor, M.: Garment replacement in monocular video sequences. ACM Trans. Graph. 34(1), 6:1\u20136:10 (2014)","journal-title":"ACM Trans. Graph."},{"key":"28_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1007\/978-3-319-24947-6_34","volume-title":"Pattern Recognition","author":"J Romero","year":"2015","unstructured":"Romero, J., Loper, M., Black, M.J.: FlowCap: 2D human pose from optical flow. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 412\u2013423. Springer, Cham (2015). doi: 10.1007\/978-3-319-24947-6_34"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Sapp, B., Weiss, D., Taskar, B.: Parsing human motion with stretchable models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1281\u20131288. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995607"},{"key":"28_CR31","unstructured":"Sigal, L., Balan, A., Black, M.J.: Combined discriminative and generative articulated pose and non-rigid shape estimation. In: Advances in Neural Information Processing Systems, pp. 1337\u20131344 (2007)"},{"issue":"1\u20132","key":"28_CR32","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal, L., Balan, A.O., Black, M.J.: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. 87(1\u20132), 4\u201327 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Simo-Serra, E., Ramisa, A., Aleny, G., Torras, C., Moreno-Noguer, F.: Single image 3D human pose estimation from noisy observations. In: Conference on Computer Vision and Pattern Recognition, pp. 2673\u20132680. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247988"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Vedula, S., Baker, S., Rander, P., Collins, R., Kanade, T.: Three-dimensional scene flow. In: IEEE International Conference on Computer Vision, vol. 2, pp. 722\u2013729. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790293"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Wandt, B., Ackermann, H., Rosenhahn, B.: 3D human motion capture from monocular image sequences. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, June 2015","DOI":"10.1109\/CVPRW.2015.7301286"},{"key":"28_CR36","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/TPAMI.2016.2553028","volume":"38","author":"B Wandt","year":"2016","unstructured":"Wandt, B., Ackermann, H., Rosenhahn, B.: 3D reconstruction of human motion from monocular image sequences. Trans. Pattern Anal. Mach. Intell. 38, 1505\u20131516 (2016)","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"28_CR37","doi-asserted-by":"crossref","first-page":"1744","DOI":"10.1109\/TPAMI.2011.236","volume":"34","author":"L Xu","year":"2012","unstructured":"Xu, L., Jia, J., Matsushita, Y.: Motion detail preserving optical flow estimation. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1744\u20131757 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, S., Fu, H., Liu, L., Cohen-Or, D., Han, X.: Parametric reshaping of human bodies in images. In: ACM Transactions on Graphics (TOG), vol. 29, p. 126. ACM (2010)","DOI":"10.1145\/1833349.1778863"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, X., Leonardos, S., Hu, X., Daniilidis, K.: 3D shape estimation from 2D landmarks: a convex relaxation approach. In: CVPR, pp. 4447\u20134455. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7299074"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhu, M., Leonardos, S., Derpanis, K.G., Daniilidis, K.: Sparseness meets deepness: 3D human pose estimation from monocular video. In: Conference on Computer Vision and Pattern Recognition, June 2016","DOI":"10.1109\/CVPR.2016.537"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Zuffi, S., Romero, J., Schmid, C., Black, M.J.: Estimating human pose with flowing puppets. IEEE International Conference on Computer Vision, pp. 3312\u20133319 (2013)","DOI":"10.1109\/ICCV.2013.411"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66709-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T22:30:37Z","timestamp":1750804237000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66709-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319667089","9783319667096"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66709-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}