{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T09:55:55Z","timestamp":1763978155938,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"10-11","license":[{"start":{"date-parts":[[2020,6,24]],"date-time":"2020-06-24T00:00:00Z","timestamp":1592956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,24]],"date-time":"2020-06-24T00:00:00Z","timestamp":1592956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s11263-020-01335-w","type":"journal-article","created":{"date-parts":[[2020,6,24]],"date-time":"2020-06-24T08:02:31Z","timestamp":1592985751000},"page":"2651-2664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Inferring 3D Shapes from Image Collections Using Adversarial Networks"],"prefix":"10.1007","volume":"128","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4971-7980","authenticated-orcid":false,"given":"Matheus","family":"Gadelha","sequence":"first","affiliation":[]},{"given":"Aartika","family":"Rai","sequence":"additional","affiliation":[]},{"given":"Subhransu","family":"Maji","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,24]]},"reference":[{"key":"1335_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., & Guibas, L. J. (2017). Learning representations and generative models for 3d point clouds. arXiv preprint arXiv:1707.02392."},{"key":"1335_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., & Schiele, B. (2010). Monocular 3D pose estimation and tracking by detection. In Computer vision and pattern recognition (CVPR). IEEE.","DOI":"10.1109\/CVPR.2010.5540156"},{"key":"1335_CR3","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1109\/TPAMI.2014.2377712","volume":"37","author":"JT Barron","year":"2015","unstructured":"Barron, J. T., & Malik, J. (2015). Shape, illumination, and reflectance from shading. Transactions of Pattern Analysis and Machine Intelligence (PAMI), 37, 1670\u20131687.","journal-title":"Transactions of Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"1335_CR4","unstructured":"Barrow, H., & Tenenbaum, J. (1978). Recovering intrinsic scene characteristics. In A. Hanson & E. Riseman (Eds.), Comput. vis. syst. (pp. 3\u201326)."},{"key":"1335_CR5","doi-asserted-by":"crossref","unstructured":"Blanz, V., & Vetter, T. (1999). A morphable model for the synthesis of 3d faces. In Proceedings of the 26th annual conference on computer graphics and interactive techniques (pp. 187\u2013194). ACM Press\/Addison-Wesley Publishing Co.","DOI":"10.1145\/311535.311556"},{"key":"1335_CR6","unstructured":"Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., & Su, H., et\u00a0al. (2015). Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012."},{"key":"1335_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Gadelha, M., Maji, S., & Sheldon, D. (2019). A Bayesian perspective on the deep image prior. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00559"},{"key":"1335_CR8","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Tobias\u00a0Springenberg, J., & Brox, T. (2015). Learning to generate chairs with convolutional neural networks. In Conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"1335_CR9","doi-asserted-by":"crossref","unstructured":"Eigen, D., & Fergus, R. (2015). Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.304"},{"key":"1335_CR10","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., & Guibas, L. J. (2017). A point set generation network for 3D object reconstruction from a single image. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.264"},{"key":"1335_CR11","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Maji, S., & Wang, R. (2017). 3D shape generation using spatially ordered point clouds. In British machine vision conference (BMVC).","DOI":"10.5244\/C.31.54"},{"key":"1335_CR12","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Maji, S., & Wang, R. (2017). 3D shape induction from 2D views of multiple objects. In International conference on 3D vision (3DV).","DOI":"10.1109\/3DV.2017.00053"},{"key":"1335_CR13","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Wang, R., & Maji, S. (2018). Multiresolution tree networks for 3D point cloud processing. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01234-2_7"},{"key":"1335_CR14","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Wang, R., & Maji, S. (2019). Shape reconstruction using differentiable projections and deep priors. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2019.00011"},{"key":"1335_CR15","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems (NIPS)."},{"key":"1335_CR16","unstructured":"Gretton, A., Borgwardt, K.\u00a0M., Rasch, M., Sch\u00f6lkopf, B., & Smola, A.\u00a0J. (2006). A kernel method for the two-sample-problem. In Advances in neural information processing systems (NIPS)."},{"key":"1335_CR17","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V.\u00a0G., Russell, B., & Aubry, M. (2018). AtlasNet: A Papier-M\u00e2ch\u00e9 approach to learning 3D surface generation. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00030"},{"key":"1335_CR18","volume-title":"Multiple view geometry in computer vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., & Zisserman, A. (2003). Multiple view geometry in computer vision. Cambridge: Cambridge University Press."},{"key":"1335_CR19","unstructured":"Henderson, P., & Ferrari, V. (2018). Learning to generate and reconstruct 3D meshes with only 2D supervision. In British machine vision conference (BMVC)."},{"key":"1335_CR20","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A.\u00a0A., & Hebert, M. (2005). Geometric context from a single image. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2005.107"},{"key":"1335_CR21","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Tulsiani, S., Efros, A.\u00a0A., & Malik, J. (2018). Learning category-specific mesh reconstruction from image collections. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01267-0_23"},{"key":"1335_CR22","doi-asserted-by":"crossref","unstructured":"Kar, A., Tulsiani, S., Carreira, J., & Malik, J. (2015). Category-specific object reconstruction from a single image. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298807"},{"key":"1335_CR23","doi-asserted-by":"crossref","unstructured":"Kato, H., Ushiku, Y., & Harada, T. (2018). Neural 3d mesh renderer. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00411"},{"key":"1335_CR24","unstructured":"Kulkarni, T.\u00a0D., Whitney, W.\u00a0F., Kohli, P., & Tenenbaum, J. (2015). Deep convolutional inverse graphics network. In Advances in neural information processing systems (NIPS)."},{"issue":"1","key":"1335_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1364\/JOSA.61.000001","volume":"61","author":"EH Land","year":"1971","unstructured":"Land, E. H., & McCann, J. J. (1971). Lightness and retinex theory. JOSA, 61(1), 1\u201311.","journal-title":"JOSA"},{"issue":"2","key":"1335_CR26","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/34.273735","volume":"16","author":"A Laurentini","year":"1994","unstructured":"Laurentini, A. (1994). The visual hull concept for silhouette-based image understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(2), 150\u2013162.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1335_CR27","first-page":"1","volume":"37","author":"T-M Li","year":"2018","unstructured":"Li, T.-M., Aittala, M., Durand, F., & Lehtinen, J. (2018). Differentiable monte carlo ray tracing through edge sampling. ACM Transactions on Graph (SIGGRAPH Asia), 37, 1\u201311.","journal-title":"ACM Transactions on Graph (SIGGRAPH Asia)"},{"key":"1335_CR28","doi-asserted-by":"crossref","unstructured":"Lin, C.-H., Kong, C., & Lucey, S. (2018). Learning efficient point cloud generation for dense 3D object reconstruction. In AAAI conference on artificial intelligence (AAAI).","DOI":"10.1609\/aaai.v32i1.12278"},{"key":"1335_CR29","first-page":"221","volume":"37","author":"HTD Liu","year":"2018","unstructured":"Liu, H. T. D., Tao, M., & Jacobson, A. (2018). Paparazzi: Surface editing by way of multi-view image processing. ACM Transactions on Graphcs, 37, 221.","journal-title":"ACM Transactions on Graphcs"},{"key":"1335_CR30","doi-asserted-by":"crossref","unstructured":"Lun, Z., Gadelha, M., Kalogerakis, E., Maji, S., & Wang, R. (2017). 3D shape reconstruction from sketches via multi-view convolutional networks. In International conference on 3D vision (3DV) (pp. 67\u201377).","DOI":"10.1109\/3DV.2017.00018"},{"key":"1335_CR31","unstructured":"Maas, A.\u00a0L., Hannun, A.\u00a0Y., & Ng, A.\u00a0Y. (2013). Rectifier nonlinearities improve neural network acoustic models. In International conference on machine learning (ICML)."},{"key":"1335_CR32","doi-asserted-by":"crossref","unstructured":"Nalbach, O., Arabadzhiyska, E., Mehta, D., Seidel, H.-P., & Ritschel, T. (2016). Deep shading: Convolutional neural networks for screen-space shading. arXiv preprint arXiv:1603.06078.","DOI":"10.1111\/cgf.13225"},{"key":"1335_CR33","unstructured":"Nguyen-Phuoc, T., Li, C., Balaban, S., & Yang, Y.-L. (2018). Rendernet: A deep convolutional network for differentiable rendering from 3d shapes. In Advances in neural information processing systems 31."},{"key":"1335_CR34","doi-asserted-by":"crossref","unstructured":"Odena, A., Dumoulin, V., & Olah, C. (2016). Deconvolution and checkerboard artifacts. Distill.","DOI":"10.23915\/distill.00003"},{"key":"1335_CR35","unstructured":"Radford, A., Metz, L., & Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434."},{"key":"1335_CR36","unstructured":"Rezende, D.\u00a0J., Eslami, S. M., Mohamed, S., Battaglia, P., Jaderberg, M., & Heess, N. (2016). Unsupervised learning of 3D structure from images. In Advances in neural information processing systems (NIPS)."},{"key":"1335_CR37","doi-asserted-by":"crossref","unstructured":"Savarese, S., & Fei-Fei, L. (2007). 3D generic object categorization, localization and pose estimation. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2007.4408987"},{"key":"1335_CR38","unstructured":"Saxena, A., Chung, S.\u00a0H., & Ng, A. (2005). Learning depth from single monocular images. In Advances in neural information processing systems (NIPS)."},{"key":"1335_CR39","doi-asserted-by":"crossref","unstructured":"Schwing, A.\u00a0G., & Urtasun, R. (2012). Efficient exact inference for 3d indoor scene understanding. In European conference on computer vision (ECCV).","DOI":"10.1109\/CVPR.2012.6248006"},{"key":"1335_CR40","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.\u00a0R., Li, Y., & Guibas, L.\u00a0J. (2015). Render for CNN: Viewpoint estimation in images using cnns trained with rendered 3D model views. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.308"},{"key":"1335_CR41","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Dosovitskiy, A., & Brox, T. (2016). Multi-view 3D models from single images with a convolutional network. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46478-7_20"},{"key":"1335_CR42","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Carreira, J., & Malik, J.. (2015). Pose induction for novel object categories. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.16"},{"key":"1335_CR43","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Efros, A.\u00a0A., & Malik, J. (2018). Multi-view consistency as supervisory signal for learning shape and pose prediction. In Computer vision and pattern regognition (CVPR).","DOI":"10.1109\/CVPR.2018.00306"},{"key":"1335_CR44","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Zhou, T., Efros, A.\u00a0A., & Malik, J. (2017). Multi-view supervision for single-view reconstruction via differentiable ray consistency. In Computer vision and pattern regognition (CVPR).","DOI":"10.1109\/CVPR.2017.30"},{"issue":"1","key":"1335_CR45","doi-asserted-by":"publisher","first-page":"191139","DOI":"10.1117\/12.7972479","volume":"19","author":"RJ Woodham","year":"1980","unstructured":"Woodham, R. J. (1980). Photometric method for determining surface orientation from multiple images. Optical Engineering, 19(1), 191139\u2013191139.","journal-title":"Optical Engineering"},{"key":"1335_CR46","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015). 3d shapenets: A deep representation for volumetric shapes. In Conference on computer vision and pattern recognition (CVPR)."},{"key":"1335_CR47","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.\u00a0T., & Tenenbaum, J.\u00a0B. (2016). Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In Advances in neural information processing systems (NIPS)."},{"key":"1335_CR48","unstructured":"Yan, X., Yang, J., Yumer, E., Guo, Y., & Lee, H. (2016). Perspective transformer nets: Learning single-view 3D object reconstruction without 3D supervision. In Advances in neural information processing systems."},{"key":"1335_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., & Efros, A.\u00a0A. (2016). View synthesis by appearance flow. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46493-0_18"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01335-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01335-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01335-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T05:27:17Z","timestamp":1667107637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01335-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,24]]},"references-count":49,"journal-issue":{"issue":"10-11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1335"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01335-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2020,6,24]]},"assertion":[{"value":"16 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}