{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:14:27Z","timestamp":1791159267713,"version":"4.1.0"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2007,8,16]],"date-time":"2007-08-16T00:00:00Z","timestamp":1187222400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/2.0"},{"start":{"date-parts":[[2007,8,16]],"date-time":"2007-08-16T00:00:00Z","timestamp":1187222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/2.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2008,1]]},"DOI":"10.1007\/s11263-007-0071-y","type":"journal-article","created":{"date-parts":[[2007,8,15]],"date-time":"2007-08-15T16:17:12Z","timestamp":1187194632000},"page":"53-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":466,"title":["3-D Depth Reconstruction from a Single Still Image"],"prefix":"10.1007","volume":"76","author":[{"given":"Ashutosh","family":"Saxena","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung H.","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew Y.","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2007,8,16]]},"reference":[{"issue":"3","key":"71_CR1","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1145\/1073204.1073207","volume":"24","author":"D. Anguelov","year":"2005","unstructured":"Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., & Davis, J. (2005). SCAPE: shape completion and animation of people. ACM Transactions on Graphics, 24(3), 408\u2013416.","journal-title":"ACM Transactions on Graphics"},{"key":"71_CR2","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/BF01420984","volume":"12","author":"J. L. Barron","year":"1994","unstructured":"Barron, J. L., Fleet, D. J., & Beauchemin, S. S. (1994). Performance of optical flow techniques. International Journal of Computer Vision, 12, 43\u201377.","journal-title":"International Journal of Computer Vision"},{"issue":"8","key":"71_CR3","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1109\/TPAMI.2003.1217603","volume":"25","author":"M. Z. Brown","year":"2003","unstructured":"Brown, M. Z., Burschka, D., & Hager, G. D. (2003). Advances in computational stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(8), 993\u20131008.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"71_CR4","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1038\/699","volume":"1","author":"I. Bulthoff","year":"1998","unstructured":"Bulthoff, I., Bulthoff, H., & Sinha, P. (1998). Top-down influences on stereoscopic depth-perception. Nature Neuroscience, 1, 254\u2013257.","journal-title":"Nature Neuroscience"},{"key":"71_CR5","doi-asserted-by":"crossref","unstructured":"Cornelis, N., Leibe, B., Cornelis, K., & Van Gool, L. (2006). 3d city modeling using cognitive loops. In Video proceedings of CVPR (VPCVPR).","DOI":"10.1109\/3DPVT.2006.1"},{"key":"71_CR6","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1026598000963","volume":"40","author":"A. Criminisi","year":"2000","unstructured":"Criminisi, A., Reid, I., & Zisserman, A. (2000). Single view metrology. International Journal of Computer Vision, 40, 123\u2013148.","journal-title":"International Journal of Computer Vision"},{"issue":"12","key":"71_CR7","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1109\/34.476513","volume":"17","author":"S. Das","year":"1995","unstructured":"Das, S., & Ahuja, N. (1995). Performance analysis of stereo, vergence, and focus as depth cues for active vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(12), 1213\u20131219.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"71_CR8","volume-title":"Machine vision: theory, algorithms, practicalities","author":"E. R. Davies","year":"1997","unstructured":"Davies, E. R. (1997). Laws\u2019 texture energy in texture. In Machine vision: theory, algorithms, practicalities (2nd\u00a0ed.). San Diego: Academic Press.","edition":"2"},{"key":"71_CR9","unstructured":"Delage, E., Lee, H., & Ng, A. Y. (2005). Automatic single-image 3d reconstructions of indoor Manhattan world scenes. In 12th International Symposium of Robotics Research (ISRR)."},{"key":"71_CR10","doi-asserted-by":"crossref","unstructured":"Delage, E., Lee, H., & Ng, A. Y. (2006). A dynamic Bayesian network model for autonomous 3D reconstruction from a single indoor image. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2006.23"},{"key":"71_CR11","volume-title":"Computer vision: a modern approach","author":"D. A. Forsyth","year":"2003","unstructured":"Forsyth, D. A., & Ponce, J. (2003). Computer vision: a modern approach. New York: Prentice Hall."},{"key":"71_CR12","doi-asserted-by":"crossref","unstructured":"Frueh, C., & Zakhor, A. (2003). Constructing 3D city models by merging ground-based and airborne views. In Computer vision and pattern recognition (CVPR).","DOI":"10.1007\/978-3-540-39798-4_39"},{"key":"71_CR13","unstructured":"Gini, G., & Marchi, A. (2002). Indoor robot navigation with single camera vision. In PRIS."},{"key":"71_CR14","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1038\/267346a0","volume":"267","author":"L. Harkness","year":"1977","unstructured":"Harkness, L. (1977). Chameleons use accommodation cues to judge distance. Nature, 267, 346\u2013349.","journal-title":"Nature"},{"key":"71_CR15","unstructured":"He, X., Zemel, R., & Perpinan, M. (2004). Multiscale conditional random fields for image labeling. In Computer vision and pattern recognition (CVPR)."},{"issue":"8","key":"71_CR16","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/TPAMI.2005.158","volume":"27","author":"A. Hertzmann","year":"2005","unstructured":"Hertzmann, A., & Seitz, S. M. (2005). Example-based photometric stereo: Shape reconstruction with general, varying brdfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1254\u20131264.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"71_CR17","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A. A., & Herbert, M. (2005a). Geometric context from a single image. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2005.107"},{"key":"71_CR18","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A. A., & Herbert, M. (2005b). Automatic photo pop-up. In ACM SIGGRAPH.","DOI":"10.1145\/1186822.1073232"},{"key":"71_CR19","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A. A., & Herbert, M. (2006). Putting objects in perspective. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2006.232"},{"key":"71_CR20","unstructured":"Huang, J., Lee, A. B., & Mumford, D. (2000). Statistics of range images. In Computer vision and pattern recognition (CVPR)."},{"issue":"9","key":"71_CR21","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2006.193","volume":"28","author":"V. Kolmogorov","year":"2006","unstructured":"Kolmogorov, V., Criminisi, A., Blake, A., Cross, G., & Rother, C. (2006). Probabilistic fusion of stereo with color and contrast for bilayer segmentation. IEEE Pattern Analysis and Machine Intelligence, 28(9), 1480\u20131492.","journal-title":"IEEE Pattern Analysis and Machine Intelligence"},{"key":"71_CR22","doi-asserted-by":"crossref","unstructured":"Konishi, S., & Yuille, A. (2000). Statistical cues for domain specific image segmentation with performance analysis. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2000.855809"},{"key":"71_CR23","unstructured":"Kumar, S., & Hebert, M. (2003). Discriminative fields for modeling spatial dependencies in natural images. In Neural information processing systems (NIPS) (Vol.\u00a016)."},{"key":"71_CR24","unstructured":"Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: probabilistic models for segmenting and labeling sequence data. In International conference on machine learning (ICML)."},{"key":"71_CR25","doi-asserted-by":"crossref","unstructured":"Lindeberg, T., & Garding, J. (1993). Shape from texture from a multi-scale perspective. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.1993.378146"},{"key":"71_CR26","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1038\/35102648","volume":"414","author":"J. M. Loomis","year":"2001","unstructured":"Loomis, J. M. (2001). Looking down is looking up. Nature News and Views, 414, 155\u2013156.","journal-title":"Nature News and Views"},{"issue":"2","key":"71_CR27","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1023\/A:1016057422703","volume":"48","author":"A. Maki","year":"2002","unstructured":"Maki, A., Watanabe, M., & Wiles, C. (2002). Geotensity: combining motion and lighting for 3d surface reconstruction. International Journal of Computer Vision, 48(2), 75\u201390.","journal-title":"International Journal of Computer Vision"},{"issue":"5","key":"71_CR28","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1364\/JOSAA.7.000923","volume":"7","author":"J. Malik","year":"1990","unstructured":"Malik, J., & Perona, P. (1990). Preattentive texture discrimination with early vision mechanisms. Journal of the Optical Society of America A, 7(5), 923\u2013932.","journal-title":"Journal of the Optical Society of America A"},{"issue":"2","key":"71_CR29","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1023\/A:1007958829620","volume":"23","author":"J. Malik","year":"1997","unstructured":"Malik, J., & Rosenholtz, R. (1997). Computing local surface orientation and shape from texture for curved surfaces. International Journal of Computer Vision, 23(2), 149\u2013168.","journal-title":"International Journal of Computer Vision"},{"key":"71_CR30","doi-asserted-by":"crossref","unstructured":"Michels, J., Saxena, A., & Ng, A. Y. (2005). High speed obstacle avoidance using monocular vision and reinforcement learning. In 22nd international conference on machine learning (ICML).","DOI":"10.1145\/1102351.1102426"},{"key":"71_CR31","doi-asserted-by":"crossref","unstructured":"Moldovan, T. M., Roth, S., & Black, M. J. (2006). Denoising archival films using a learned Bayesian model. In International conference on image processing (ICIP).","DOI":"10.1109\/ICIP.2006.313052"},{"key":"71_CR32","doi-asserted-by":"crossref","unstructured":"Mortensen, E. N., Deng, H., & Shapiro, L. (2005). A SIFT descriptor with global context. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2005.45"},{"key":"71_CR33","unstructured":"Murphy, K., Torralba, A., & Freeman, W. T. (2003). Using the forest to see the trees: a\u00a0graphical model relating features, objects, and scenes. In Neural information processing systems (NIPS) (Vol.\u00a016)."},{"key":"71_CR34","doi-asserted-by":"crossref","unstructured":"Nagai, T., Naruse, T., Ikehara, M., & Kurematsu, A. (2002). Hmm-based surface reconstruction from single images. In IEEE international conference on image processing (ICIP).","DOI":"10.1109\/ICIP.2002.1040012"},{"key":"71_CR35","unstructured":"Narasimhan, S. G., & Nayar, S. K. (2003). Shedding light on the weather. In Computer vision and pattern recognition (CVPR)"},{"issue":"1","key":"71_CR36","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1117\/1.482638","volume":"7","author":"O. Nestares","year":"1998","unstructured":"Nestares, O., Navarro, R., Portilia, J., & Tabernero, A. (1998). Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. Journal of Electronic Imaging, 7(1), 166\u2013173.","journal-title":"Journal of Electronic Imaging"},{"key":"71_CR37","first-page":"23","volume":"155","author":"A. Oliva","year":"2006","unstructured":"Oliva, A., & Torralba, A. (2006). Building the gist of a scene: the role of global image features in recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 155, 23\u201336.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"71_CR38","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","volume":"37","author":"B. A. Olshausen","year":"1997","unstructured":"Olshausen, B. A., & Field, D. J. (1997). Sparse coding with an over-complete basis set: a strategy employed by v1? Vision Research, 37, 3311\u20133325.","journal-title":"Vision Research"},{"key":"71_CR39","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1038\/16244","volume":"397","author":"J. Porrill","year":"1999","unstructured":"Porrill, J., Frisby, J. P., Adams, W. J., & Buckley, D. (1999). Robust and optimal use of information in stereo vision. Nature, 397, 63\u201366.","journal-title":"Nature"},{"key":"71_CR40","doi-asserted-by":"crossref","unstructured":"Quartulli, M., & Datcu, M. (2001). Bayesian model based city reconstruction from high resolution ISAR data. In IEEE\/ISPRS joint workshop remote sensing and data fusion over urban areas.","DOI":"10.1109\/DFUA.2001.985727"},{"key":"71_CR41","unstructured":"Saxena, A., Anand, A., & Mukerjee, A. (2004). Robust facial expression recognition using spatially localized geometric model. In International conf systemics, cybernetics and informatics (ICSCI)."},{"key":"71_CR42","unstructured":"Saxena, A., Chung, S. H., & Ng, A. Y. (2005). Learning depth from single monocular images. In Neural information processing system (NIPS) (Vol.\u00a018)."},{"key":"71_CR43","unstructured":"Saxena, A., Driemeyer, J., Kearns, J., Osondu, C., & Ng, A. Y. (2006a). Learning to grasp novel objects using vision. In 10th international symposium on experimental robotics (ISER)."},{"key":"71_CR44","doi-asserted-by":"crossref","unstructured":"Saxena, A., Sun, M., Agarwal, R., & Ng, A. Y. (2006b). Learning 3-d scene structure from a single still image. Stanford Technical Report, November 2006.","DOI":"10.1109\/ICCV.2007.4408828"},{"key":"71_CR45","doi-asserted-by":"crossref","unstructured":"Saxena, A., Driemeyer, J., Kearns, J., & Ng, A. Y. (2006c). Robotic grasping of novel objects. In Neural information processing systems (NIPS) (Vol.\u00a019).","DOI":"10.7551\/mitpress\/7503.003.0156"},{"key":"71_CR46","unstructured":"Saxena, A., Schulte, J., & Ng, A. Y. (2007). Depth estimation using monocular and stereo cues. In International joint conference on artificial intelligence (IJCAI)."},{"issue":"1","key":"71_CR47","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1014573219977","volume":"47","author":"D. Scharstein","year":"2002","unstructured":"Scharstein, D., & Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1), 7\u201342.","journal-title":"International Journal of Computer Vision"},{"key":"71_CR48","unstructured":"Scharstein, D., & Szeliski, R. (2003) High-accuracy stereo depth maps using structured light. In Computer vision and pattern recognition (CVPR)."},{"key":"71_CR49","volume-title":"Visual perception","author":"S. H. Schwartz","year":"1999","unstructured":"Schwartz, S. H. (1999). Visual perception (2nd\u00a0ed.). Connecticut: Appleton and Lange.","edition":"2"},{"key":"71_CR50","doi-asserted-by":"crossref","unstructured":"Serre, T., Wolf, L., & Poggio, T. (2005). Object recognition with features inspired by visual cortex. In Computer vision and pattern recognition (CVPR).","DOI":"10.21236\/ADA454604"},{"key":"71_CR51","volume-title":"Wavelets and filter banks","author":"G. Strang","year":"1997","unstructured":"Strang, G., & Nguyen, T. (1997). Wavelets and filter banks. Wellesley: Wellesley-Cambridge Press."},{"key":"71_CR52","unstructured":"Sudderth, E. B., Torralba, A., Freeman, W. T., & Willisky, A. S. (2006). Depth from familiar objects: A hierarchical model for 3D scenes. In Computer vision and pattern recognition (CVPR)"},{"key":"71_CR53","doi-asserted-by":"crossref","unstructured":"Szeliski, R. (1990). Bayesian modeling of uncertainty in low-level vision. In International conference on computer vision (ICCV).","DOI":"10.1007\/978-1-4613-1637-4"},{"key":"71_CR54","doi-asserted-by":"crossref","unstructured":"Thrun, S., & Wegbreit, B. (2005). Shape from symmetry. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2005.221"},{"issue":"9","key":"71_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2002.1033214","volume":"24","author":"A. Torralba","year":"2002","unstructured":"Torralba, A., & Oliva, A. (2002). Depth estimation from image structure. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(9), 1\u201313.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"71_CR56","doi-asserted-by":"crossref","unstructured":"Torresani, L., & Hertzmann, A. (2004). Automatic non-rigid 3D modeling from video. In European conference on computer vision.","DOI":"10.1007\/978-3-540-24671-8_24"},{"key":"71_CR57","volume-title":"Foundations of vision","author":"B. A. Wandell","year":"1995","unstructured":"Wandell, B. A. (1995). Foundations of vision. Sunderland: Sinauer Associates."},{"key":"71_CR58","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1038\/nn1461","volume":"8","author":"A. E. Welchman","year":"2005","unstructured":"Welchman, A. E., Deubelius, A., Conrad, V., B\u00fclthoff, H. H., & Kourtzi, Z. (2005). 3D shape perception from combined depth cues in human visual cortex. Nature Neuroscience, 8, 820\u2013827.","journal-title":"Nature Neuroscience"},{"key":"71_CR59","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1038\/35051081","volume":"409","author":"M. Wexler","year":"2001","unstructured":"Wexler, M., Panerai, F., Lamouret, I., & Droulez, J. (2001). Self-motion and the perception of stationary objects. Nature, 409, 85\u201388.","journal-title":"Nature"},{"issue":"8","key":"71_CR60","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.1109\/JPROC.2002.800717","volume":"90","author":"A. S. Willsky","year":"2002","unstructured":"Willsky, A. S. (2002). Multiresolution Markov models for signal and image processing. Proceedings IEEE, 90(8), 1396\u20131458.","journal-title":"Proceedings IEEE"},{"key":"71_CR61","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1038\/nature02350","volume":"428","author":"B. Wu","year":"2004","unstructured":"Wu, B., Ooi, T. L., & He, Z. J. (2004). Perceiving distance accurately by a directional process of integrating ground information. Letters to Nature, 428, 73\u201377.","journal-title":"Letters to Nature"},{"issue":"8","key":"71_CR62","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/34.784284","volume":"21","author":"R. Zhang","year":"1999","unstructured":"Zhang, R., Tsai, P.-S., Cryer, J. E., & Shah, M. (1999). Shape from shading: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(8), 690\u2013706.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"71_CR63","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1145\/954339.954342","volume":"35","author":"W. Zhao","year":"2003","unstructured":"Zhao, W., Chellappa, R., Phillips, P. J., & Rosenfield, A. (2003). Face recognition: a\u00a0literature survey. ACM Computing Surveys, 35, 399\u2013458.","journal-title":"ACM Computing Surveys"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-007-0071-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-007-0071-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-007-0071-y.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-007-0071-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T11:45:16Z","timestamp":1708170316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-007-0071-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,8,16]]},"references-count":63,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2008,1]]}},"alternative-id":["71"],"URL":"https:\/\/doi.org\/10.1007\/s11263-007-0071-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,8,16]]},"assertion":[{"value":"1 November 2006","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2007","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2007","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}