{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:13:23Z","timestamp":1779383603700,"version":"3.53.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464657","type":"print"},{"value":"9783319464664","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46466-4_22","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T09:31:58Z","timestamp":1474018318000},"page":"365-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":94,"title":["Single Image 3D Interpreter Network"],"prefix":"10.1007","author":[{"given":"Jiajun","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianfan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph J.","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuandong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William T.","family":"Freeman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3d human pose reconstruction. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Aubry, M., Maturana, D., Efros, A., Russell, B., Sivic, J.: Seeing 3d chairs: exemplar part-based 2d\u20133d alignment using a large dataset of cad models. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.487"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Bansal, A., Russell, B.: Marr revisited: 2d\u20133d alignment via surface normal prediction. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.642"},{"issue":"12","key":"22_CR4","doi-asserted-by":"publisher","first-page":"2930","DOI":"10.1109\/TPAMI.2013.23","volume":"35","author":"PN Belhumeur","year":"2013","unstructured":"Belhumeur, P.N., Jacobs, D.W., Kriegman, D.J., Kumar, N.: Localizing parts of faces using a consensus of exemplars. IEEE TPAMI 35(12), 2930\u20132940 (2013)","journal-title":"IEEE TPAMI"},{"issue":"2\u20133","key":"22_CR5","doi-asserted-by":"crossref","first-page":"174","DOI":"10.5964\/bioling.8783","volume":"4","author":"TG Bever","year":"2010","unstructured":"Bever, T.G., Poeppel, D.: Analysis by synthesis: a (re-) emerging program of research for language and vision. Biolinguistics 4(2\u20133), 174\u2013200 (2010)","journal-title":"Biolinguistics"},{"key":"22_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1007\/978-3-642-15567-3_13","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L Bourdev","year":"2010","unstructured":"Bourdev, L., Maji, S., Brox, T., Malik, J.: Detecting people using mutually consistent poselet activations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 168\u2013181. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15567-3_13"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"22_CR8","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Christopher B. Choy","year":"2016","unstructured":"Choy, C.B., Xu, D., Gwak, J., Chen, K., Savarese, S.: 3d\u2013r2n2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2006, Part VIII. LNCS, vol. 9912, pp. 1\u201317. Springer, Heidelberg (2016)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Tobias Springenberg, J., Brox, T.: Learning to generate chairs with convolutional neural networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"22_CR10","unstructured":"Fidler, S., Dickinson, S.J., Urtasun, R.: 3d object detection and viewpoint estimation with a deformable 3d cuboid model. In: NIPS (2012)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Hejrati, M., Ramanan, D.: Analysis by synthesis: 3d object recognition by object reconstruction. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.314"},{"key":"22_CR13","unstructured":"Hejrati, M., Ramanan, D.: Analyzing 3d objects in cluttered images. In: NIPS (2012)"},{"issue":"1358","key":"22_CR14","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1098\/rstb.1997.0101","volume":"352","author":"GE Hinton","year":"1997","unstructured":"Hinton, G.E., Ghahramani, Z.: Generative models for discovering sparse distributed representations. Philos. Trans. R. Soc. London B: Biol. Sci. 352(1358), 1177\u20131190 (1997)","journal-title":"Philos. Trans. R. Soc. London B: Biol. Sci."},{"issue":"6","key":"22_CR15","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1109\/TPAMI.2014.2362141","volume":"37","author":"W Hu","year":"2015","unstructured":"Hu, W., Zhu, S.C.: Learning 3d object templates by quantizing geometry and appearance spaces. IEEE TPAMI 37(6), 1190\u20131205 (2015)","journal-title":"IEEE TPAMI"},{"issue":"4","key":"22_CR16","first-page":"87","volume":"34","author":"Q Huang","year":"2015","unstructured":"Huang, Q., Wang, H., Koltun, V.: Single-view reconstruction via joint analysis of image and shape collections. ACM SIGGRAPH 34(4), 87 (2015)","journal-title":"ACM SIGGRAPH"},{"key":"22_CR17","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: NIPS (2015)"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Kar, A., Tulsiani, S., Carreira, J., Malik, J.: Category-specific object reconstruction from a single image. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298807"},{"key":"22_CR19","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Kulkarni, T.D., Kohli, P., Tenenbaum, J.B., Mansinghka, V.: Picture: a probabilistic programming language for scene perception. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299068"},{"key":"22_CR21","unstructured":"Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.B.: Deep convolutional inverse graphics network. In: NIPS (2015)"},{"issue":"2","key":"22_CR22","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/BF00129683","volume":"9","author":"YG Leclerc","year":"1992","unstructured":"Leclerc, Y.G., Fischler, M.A.: An optimization-based approach to the interpretation of single line drawings as 3d wire frames. IJCV 9(2), 113\u2013136 (1992)","journal-title":"IJCV"},{"issue":"6","key":"22_CR23","first-page":"234","volume":"34","author":"Y Li","year":"2015","unstructured":"Li, Y., Su, H., Qi, C.R., Fish, N., Cohen-Or, D., Guibas, L.J.: Joint embeddings of shapes and images via cnn image purification. ACM SIGGRAPH Asia 34(6), 234 (2015)","journal-title":"ACM SIGGRAPH Asia"},{"key":"22_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1007\/978-3-319-10599-4_31","volume-title":"Computer Vision \u2013 ECCV 2014","author":"JJ Lim","year":"2014","unstructured":"Lim, J.J., Khosla, A., Torralba, A.: FPM: fine pose parts-based model with 3D CAD models. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 478\u2013493. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10599-4_31"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Lim, J.J., Pirsiavash, H., Torralba, A.: Parsing ikea objects: fine pose estimation. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.372"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., Belhumeur, P.N.: Bird part localization using exemplar-based models with enforced pose and subcategory consistency. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.313"},{"issue":"3","key":"22_CR27","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/0004-3702(87)90070-1","volume":"31","author":"DG Lowe","year":"1987","unstructured":"Lowe, D.G.: Three-dimensional object recognition from single two-dimensional images. Artif. Intell. 31(3), 355\u2013395 (1987). Elsevier","journal-title":"Artif. Intell."},{"issue":"11","key":"22_CR28","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. JMLR 9(11), 2579\u20132605 (2008)","journal-title":"JMLR"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. arXiv preprint arXiv:1603.06937 (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"22_CR30","unstructured":"Peng, X., Sun, B., Ali, K., Saenko, K.: Exploring invariances in deep convolutional neural networks using synthetic images. CoRR, abs\/1412.7122 2 (2014)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Pepik, B., Stark, M., Gehler, P., Schiele, B.: Teaching 3d geometry to deformable part models. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248075"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Prasad, M., Fitzgibbon, A., Zisserman, A., Van Gool, L.: Finding nemo: deformable object class modelling using curve matching. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539840"},{"key":"22_CR33","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":"22_CR34","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Sapp, B., Taskar, B.: Modec: multimodal decomposable models for human pose estimation. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.471"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Satkin, S., Lin, J., Hebert, M.: Data-driven scene understanding from 3D models. In: BMVC (2012)","DOI":"10.5244\/C.26.128"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Shakhnarovich, G., Viola, P., Darrell, T.: Fast pose estimation with parameter-sensitive hashing. In: ICCV (2003)","DOI":"10.1109\/ICCV.2003.1238424"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Mallya, A., Singh, S., Hoiem, D.: Part localization using multi-proposal consensus for fine-grained categorization. In: BMVC (2015)","DOI":"10.5244\/C.29.128"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A.: Building part-based object detectors via 3d geometry. In: ICCV, pp. 1745\u20131752 (2013)","DOI":"10.1109\/ICCV.2013.219"},{"issue":"4","key":"22_CR40","first-page":"37","volume":"33","author":"H Su","year":"2014","unstructured":"Su, H., Huang, Q., Mitra, N.J., Li, Y., Guibas, L.: Estimating image depth using shape collections. ACM TOG 33(4), 37 (2014)","journal-title":"ACM TOG"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.: Render for cnn: viewpoint estimation in images using cnns trained with rendered 3d model views. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Sun, B., Saenko, K.: From virtual to reality: fast adaptation of virtual object detectors to real domains. In: BMVC (2014)","DOI":"10.5244\/C.28.82"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Web-scale training for face identification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298891"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"22_CR45","unstructured":"Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NIPS (2014)"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"22_CR47","unstructured":"Torresani, L., Hertzmann, A., Bregler, C.: Learning non-rigid 3d shape from 2d motion. In: NIPS (2003)"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: CVPR, pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Malik, J.: Viewpoints and keypoints. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Vicente, S., Carreira, J., Agapito, L., Batista, J.: Reconstructing pascal voc. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.13"},{"key":"22_CR51","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report. CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"22_CR52","unstructured":"Wu, J., Yildirim, I., Lim, J.J., Freeman, B., Tenenbaum, J.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: NIPS (2015)"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond pascal: a benchmark for 3d object detection in the wild. In: WACV (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"22_CR55","unstructured":"Xue, T., Liu, J., Tang, X.: Example-based 3d object reconstruction from line drawings. In: CVPR (2012)"},{"key":"22_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Yasin, H., Iqbal, U., Kr\u00fcger, B., Weber, A., Gall, J.: A dual-source approach for 3d pose estimation from a single image. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.535"},{"issue":"7","key":"22_CR58","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.tics.2006.05.002","volume":"10","author":"A Yuille","year":"2006","unstructured":"Yuille, A., Kersten, D.: Vision as bayesian inference: analysis by synthesis? Trends Cogn. Sci. 10(7), 301\u2013308 (2006)","journal-title":"Trends Cogn. Sci."},{"key":"22_CR59","unstructured":"Zeng, A., Song, S., Nie\u00dfner, M., Fisher, M., Xiao, J.: 3dmatch: learning the matching of local 3d geometry in range scans. arXiv preprint arXiv:1603.08182 (2016)"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Zhou, T., Kr\u00e4henb\u00fchl, P., Aubry, M., Huang, Q., Efros, A.A.: Learning dense correspondence via 3d-guided cycle consistency. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.20"},{"key":"22_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, X., Leonardos, S., Hu, X., Daniilidis, K.: 3d shape reconstruction from 2d landmarks: a convex formulation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299074"},{"issue":"11","key":"22_CR62","doi-asserted-by":"publisher","first-page":"2608","DOI":"10.1109\/TPAMI.2013.87","volume":"35","author":"MZ Zia","year":"2013","unstructured":"Zia, M.Z., Stark, M., Schiele, B., Schindler, K.: Detailed 3d representations for object recognition and modeling. IEEE TPAMI 35(11), 2608\u20132623 (2013)","journal-title":"IEEE TPAMI"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46466-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T16:41:18Z","timestamp":1657298478000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46466-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464657","9783319464664"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46466-4_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}