{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T05:54:37Z","timestamp":1713419677677},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"10-11","license":[{"start":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T00:00:00Z","timestamp":1584662400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T00:00:00Z","timestamp":1584662400000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s11263-020-01322-1","type":"journal-article","created":{"date-parts":[[2020,3,20]],"date-time":"2020-03-20T14:02:44Z","timestamp":1584712964000},"page":"2478-2493","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation"],"prefix":"10.1007","volume":"128","author":[{"given":"Sai","family":"Rajeswar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahim","family":"Mannan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Golemo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00e9r\u00f4me","family":"Parent-L\u00e9vesque","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Vazquez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derek","family":"Nowrouzezahrai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Courville","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,20]]},"reference":[{"key":"1322_CR1","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In International conference on machine learning (ICML)."},{"key":"1322_CR2","unstructured":"Belghazi, M. I., Baratin, A., Rajeshwar, S., Ozair, S., Bengio, Y., Hjelm, D., & Courville, A. (2018). Mutual information neural estimation. In International conference on machine learning (ICML)."},{"key":"1322_CR3","unstructured":"Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2019). Nuscenes: A multimodal dataset for autonomous driving. arXiv:1903.11027."},{"key":"1322_CR4","unstructured":"Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., Xiao, J., Yi, L., & Yu, F. (2015). Shapenet: An information-rich 3D model repository."},{"key":"1322_CR5","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Kalogerakis, E., Guibas, L., & Koltun, V. (2011). Probabilistic reasoning for assembly-based 3D modeling. In ACM SIGGRAPH.","DOI":"10.1145\/2010324.1964930"},{"key":"1322_CR6","unstructured":"Chen, W., Gao, J., Ling, H., Smith, E. J., Lehtinen, J., Jacobson, A., & Fidler, S. (2019). Learning to predict 3d objects with an interpolation-based differentiable renderer. CoRR abs\/1908.01210"},{"key":"1322_CR7","doi-asserted-by":"crossref","unstructured":"Choy, C., Xu, D., Gwak, J., Chen, K., & Savarese, S. (2016). 3D-r2n2: A unified approach for single and multi-view 3d object reconstruction.","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"1322_CR8","unstructured":"Donahue, J., & Kr\u00e4henb, U. P., & Darrell, T. (2016). Adversarial feature learning. arXiv:1605.09782."},{"key":"1322_CR9","unstructured":"Dumoulin, V., Belghazi, I., Poole, B., Lamb, A., Arjovsky, M., Mastropietro, O., & Courville, A. (2016). Adversarially learned inference. arXiv:1606.00704."},{"key":"1322_CR10","unstructured":"Gadelha, M., Maji, S., & Wang, R. (2016). 3D shape induction from 2D views of multiple objects. CoRR abs\/1612.05872."},{"key":"1322_CR11","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Fouhey, D., Rodriguez, M., & Gupta, A. (2016). Learning a predictable and generative vector representation for objects. In European conference of computer vision (ECCV).","DOI":"10.1007\/978-3-319-46466-4_29"},{"key":"1322_CR12","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":"1322_CR13","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M,, Dumoulin, V., & Courville, A. C. (2017). Improved training of wasserstein gans. In Advances in neural information processing systems (NIPS)."},{"key":"1322_CR14","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., & LeCun, Y. (2006). Dimensionality reduction by learning an invariant mapping. In Null.","DOI":"10.1109\/CVPR.2006.100"},{"key":"1322_CR15","volume-title":"Grundz\u00fcge der Mengenlehre","author":"F Hausdorff","year":"1949","unstructured":"Hausdorff, F. (1949). Grundz\u00fcge der Mengenlehre. New York: Chelsea Pub. Co."},{"key":"1322_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1322_CR17","unstructured":"Henderson, P., & Ferrari, V. (2018). Learning to generate and reconstruct 3D meshes with only 2D supervision. CoRR abs\/1807.09259."},{"key":"1322_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhou, Y., Funkhouser, T. A., & Guibas, L. J. (2019). Framenet: Learning local canonical frames of 3D surfaces from a single RGB image. CoRR abs\/1903.12305.","DOI":"10.1109\/ICCV.2019.00873"},{"key":"1322_CR19","unstructured":"Insafutdinov, E., & Dosovitskiy, A. (2018). Unsupervised learning of shape and pose with differentiable point clouds. CoRR abs\/1810.09381."},{"key":"1322_CR20","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (ICML)."},{"key":"1322_CR21","unstructured":"Jiang, C. M., Wang, D., Huang, J., Marcus, P., & Nie\u00dfner, M. (2019). Convolutional neural networks on non-uniform geometrical signals using euclidean spectral transformation. CoRR abs\/1901.02070."},{"key":"1322_CR22","doi-asserted-by":"crossref","unstructured":"Kajiya, J. T. (1986). The rendering equation. In Annual conference on computer graphics and interactive techniques (SIGGRAPH).","DOI":"10.1145\/15922.15902"},{"issue":"4","key":"1322_CR23","doi-asserted-by":"publisher","first-page":"55-1","DOI":"10.1145\/2185520.2185551","volume":"31","author":"E Kalogerakis","year":"2012","unstructured":"Kalogerakis, E., Chaudhuri, S., Koller, D., & Koltun, V. (2012). A probabilistic model for component-based shape synthesis. ACM Transactions in Graphics, 31(4), 55-1\u201355-11.","journal-title":"ACM Transactions in Graphics"},{"key":"1322_CR24","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Tulsiani, S., Efros, A. A., & 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":"1322_CR25","unstructured":"Kar, A., Tulsiani, S., Carreira, J., & Malik, J. (2014). Category-specific object reconstruction from a single image. CoRR abs\/1411.6069."},{"key":"1322_CR26","unstructured":"Kato, H., & Harada, T. (2018). Learning view priors for single-view 3D reconstruction. CoRR abs\/1811.10719."},{"key":"1322_CR27","unstructured":"Kato, H., Ushiku, Y., & Harada, T. (2017). Neural 3D mesh renderer. CoRR abs\/1711.07566."},{"issue":"6","key":"1322_CR28","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/j.cag.2004.08.009","volume":"28","author":"L Kobbelt","year":"2004","unstructured":"Kobbelt, L., & Botsch, M. (2004). A survey of point-based techniques in computer graphics. Computers and Graphics, 28(6), 801\u2013814.","journal-title":"Computers and Graphics"},{"key":"1322_CR29","unstructured":"Koch, G., Zemel, R., & Salakhutdinov, R. (2015). Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop."},{"key":"1322_CR30","unstructured":"Kulkarni, T. D., Whitney, W., Kohli, P., & Tenenbaum, J. B. (2015). Deep convolutional inverse graphics network. In Advances in neural information processing systems (NIPS)."},{"key":"1322_CR31","unstructured":"Li, C., Liu, H., Chen, C., Pu, Y., Chen, L., Henao, R., & Carin, L. (2017), Alice: Towards understanding adversarial learning for joint distribution matching. In Advances in neural information processing systems (NIPS)."},{"key":"1322_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., Dekel, T., Cole, F., Tucker, R., Snavely, N., Liu, C., & Freeman, W. T. (2019). Learning the depths of moving people by watching frozen people. CoRR abs\/1904.11111.","DOI":"10.1109\/CVPR.2019.00465"},{"key":"1322_CR33","unstructured":"Liu, S., Chen, W., Li, T., & Li, H. (2019), Soft rasterizer: Differentiable rendering for unsupervised single-view mesh reconstruction. CoRR abs\/1901.05567."},{"key":"1322_CR34","doi-asserted-by":"crossref","unstructured":"Loper, M. M., & Black, M. J. (2014). Opendr: An approximate differentiable renderer. In Euroean conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-10584-0_11"},{"key":"1322_CR35","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Deoras, A., Kombrink, S., Burget, L., & Cernock\u1ef3, J. (2011), Empirical evaluation and combination of advanced language modeling techniques. In INTERSPEECH.","DOI":"10.21437\/Interspeech.2011-242"},{"key":"1322_CR36","unstructured":"Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets."},{"key":"1322_CR37","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., & Yang, Y. L. (2019). Hologan: Unsupervised learning of 3d representations from natural images.","DOI":"10.1109\/ICCV.2019.00768"},{"key":"1322_CR38","doi-asserted-by":"crossref","unstructured":"Niu, C., Li, J., & Xu, K. (2018). Im2struct: Recovering 3d shape structure from a single RGB image. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00475"},{"key":"1322_CR39","doi-asserted-by":"crossref","unstructured":"Novotn\u00fd, D., Larlus, D., & Vedaldi, A. (2017). Learning 3D object categories by looking around them. CoRR abs\/1705.03951.","DOI":"10.1109\/ICCV.2017.558"},{"key":"1322_CR40","unstructured":"Novotn\u00fd, D., Ravi, N., Graham, B., Neverova, N., & Vedaldi, A. (2019). C3dpo: Canonical 3D pose networks for non-rigid structure from motion. arXiv:1909.02533."},{"key":"1322_CR41","unstructured":"Perez, E., Strub, F., De\u00a0Vries, H., Dumoulin, V., & Courville, A. (2017). Film: Visual reasoning with a general conditioning layer. arXiv:1709.07871."},{"key":"1322_CR42","doi-asserted-by":"crossref","unstructured":"Pfister, H., Zwicker, M., van Baar, J., & Gross, M. (2000), Surfels: Surface elements as rendering primitives. In Annual conference on computer graphics and interactive techniques.","DOI":"10.1145\/344779.344936"},{"key":"1322_CR43","unstructured":"Radford, A., Metz, L., & Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. In International conference on learning representations (ICLR)."},{"key":"1322_CR44","unstructured":"Rezende, D. J., Eslami, S. M. A., 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":"1322_CR45","doi-asserted-by":"crossref","unstructured":"Saxena, A., Sun, M., & Ng, A. Y. (2009). Make3d: Learning 3D scene structure from a single still image. In IEEE transasctions on pattern anal mach intell (PAMI) (Vol. 31, No. 5).","DOI":"10.1109\/TPAMI.2008.132"},{"issue":"3972","key":"1322_CR46","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1126\/science.171.3972.701","volume":"171","author":"RN Shepard","year":"1971","unstructured":"Shepard, R. N., & Metzler, J. (1971). Mental rotation of three-dimensional objects. Science, 171(3972), 701\u2013703.","journal-title":"Science"},{"key":"1322_CR47","doi-asserted-by":"crossref","unstructured":"Soltani, A. A., Huang, H., Wu, J., Kulkarni, T. D., & Tenenbaum, J. B. (2017). Synthesizing 3D shapes via modeling multi-view depth maps and silhouettes with deep generative networks. In Computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.269"},{"key":"1322_CR48","doi-asserted-by":"crossref","unstructured":"Taha, A. A., & Hanbury, A. (2015). An efficient algorithm for calculating the exact hausdorff distance. In IEEE transactions on pattern analysis and machine intelligence (PAMI).","DOI":"10.1109\/TPAMI.2015.2408351"},{"key":"1322_CR49","unstructured":"Tulsiani, S., Su, H., Guibas, L. J., Efros, A. A., & Malik, J. (2016), Learning shape abstractions by assembling volumetric primitives. CoRR abs\/1612.00404."},{"key":"1322_CR50","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Zhou, T., Efros, A. A., & Malik, J. (2017). Multi-view supervision for single-view reconstruction via differentiable ray consistency. CoRR abs\/1704.06254.","DOI":"10.1109\/CVPR.2017.30"},{"key":"1322_CR51","doi-asserted-by":"crossref","unstructured":"Wiles, O., & Zisserman, A. (2017). Silnet : Single- and multi-view reconstruction by learning from silhouettes. CoRR abs\/1711.07888.","DOI":"10.5244\/C.31.99"},{"key":"1322_CR52","unstructured":"Woodcock, R., Mather, N., & McGrew, K. (2001). Woodcock johnson iii\u2014tests of cognitive skills. Riverside Pub."},{"key":"1322_CR53","doi-asserted-by":"crossref","unstructured":"Wu, J., Xue, T., Lim, J., Tian, Y., Tenenbaum, J., Torralba, A., & Freeman, W. (2016a), Single image 3d interpreter network.","DOI":"10.1007\/978-3-319-46466-4_22"},{"key":"1322_CR54","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W. T., Tenenbaum, J. B. (2016b). Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In Advances in neural information processing systems (NIPS)."},{"key":"1322_CR55","unstructured":"Wu, J., Wang, Y., Xue, T., Sun, X., Freeman, W. T., & Tenenbaum, J. B. (2017). Marrnet: 3D shape reconstruction via 2.5D sketches. CoRR abs\/1711.03129."},{"key":"1322_CR56","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 Computer vision and pattern recognition (CVPR)."},{"key":"1322_CR57","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 (NIPS)."},{"key":"1322_CR58","unstructured":"Zhang, X., Zhang, Z., Zhang, C., Tenenbaum, J., Freeman, B., & Wu, J. (2018). Learning to reconstruct shapes from unseen classes. In Advances in neural information processing systems (NIPS)."},{"key":"1322_CR59","unstructured":"Zhu, J. Y, Zhang, Z., Zhang, C., Wu, J., Torralba, A., Tenenbaum, J. B., & Freeman, W. T. (2018). Visual object networks: Image generation with disentangled 3D representations. In Advances in neural information processing systems (NeurIPS)."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01322-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-020-01322-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01322-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T09:50:22Z","timestamp":1666173022000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-020-01322-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,20]]},"references-count":59,"journal-issue":{"issue":"10-11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1322"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01322-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,20]]},"assertion":[{"value":"15 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}