{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:54:45Z","timestamp":1772114085460,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"10-11","license":[{"start":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T00:00:00Z","timestamp":1590624000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T00:00:00Z","timestamp":1590624000000},"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\/s11263-020-01336-9","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T06:02:26Z","timestamp":1590645746000},"page":"2570-2585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Compositional GAN: Learning Image-Conditional Binary Composition"],"prefix":"10.1007","volume":"128","author":[{"given":"Samaneh","family":"Azadi","sequence":"first","affiliation":[]},{"given":"Deepak","family":"Pathak","sequence":"additional","affiliation":[]},{"given":"Sayna","family":"Ebrahimi","sequence":"additional","affiliation":[]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,28]]},"reference":[{"key":"1336_CR1","unstructured":"Antoniou, A., Storkey, A., & Edwards, H. (2017). Data augmentation generative adversarial networks. arXiv:1711.04340."},{"key":"1336_CR2","doi-asserted-by":"crossref","unstructured":"Azadi, S., Fisher, M., Kim, V., Wang, Z., & Shechtman, E. (2017). Multi-content GAN for few-shot font style transfer. arXiv:1712.00516.","DOI":"10.1109\/CVPR.2018.00789"},{"key":"1336_CR3","unstructured":"Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., et al. (2015). ShapeNet: An information-rich 3D model repository. Tech. Rep., Stanford University\u2014Princeton University\u2014Toyota Technological Institute at Chicago. arXiv:1512.03012 [cs.GR]."},{"key":"1336_CR4","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., & Abbeel, P. (2016). Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In NIPS."},{"key":"1336_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., et al. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1336_CR6","unstructured":"Denton, E. L., Chintala, S., Szlam, A., & Fergus, R. (2015). Deep generative image models using a Laplacian pyramid of adversarial networks. In NIPS."},{"key":"1336_CR7","unstructured":"Goodfellow, I. (2016). NIPS 2016 tutorial: Generative adversarial networks. arXiv preprint arXiv:1701.00160."},{"key":"1336_CR8","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of wasserstein GANs. In NIPS."},{"key":"1336_CR9","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167."},{"key":"1336_CR10","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2017.632"},{"key":"1336_CR11","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et\u00a0al. (2015). Spatial transformer networks. In NIPS."},{"key":"1336_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., & Fei-Fei, L. (2018). Image generation from scene graphs. In CVPR.","DOI":"10.1109\/CVPR.2018.00133"},{"key":"1336_CR13","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017). Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196."},{"key":"1336_CR14","doi-asserted-by":"crossref","unstructured":"Lai, W. S., Huang, J. B., Ahuja, N., & Yang, M. H. (2017). Deep Laplacian pyramid networks for fast and accurate super-resolution. In CVPR.","DOI":"10.1109\/CVPR.2017.618"},{"key":"1336_CR15","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., et\u00a0al. (2016). Photo-realistic single image super-resolution using a generative adversarial network. arXiv preprint.","DOI":"10.1109\/CVPR.2017.19"},{"key":"1336_CR16","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Yumer, E., Wang, O., Shechtman, E., & Lucey, S. (2018). ST-GAN: Spatial transformer generative adversarial networks for image compositing. arXiv preprint arXiv:1803.01837.","DOI":"10.1109\/CVPR.2018.00985"},{"key":"1336_CR17","unstructured":"Liu, M. Y., Breuel, T., & Kautz, J. (2017). Unsupervised image-to-image translation networks. In NIPS."},{"key":"1336_CR18","unstructured":"Liu, M. Y. , & Tuzel, O. (2016). Coupled generative adversarial networks. In Advances in neural information processing systems (pp. 469\u2013477)."},{"key":"1336_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. In ICCV.","DOI":"10.1109\/ICCV.2015.425"},{"key":"1336_CR20","unstructured":"Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784."},{"key":"1336_CR21","unstructured":"Odena, A., Olah, C., & Shlens, J. (2016). Conditional image synthesis with auxiliary classifier GANs. arXiv preprint arXiv:1610.09585."},{"key":"1336_CR22","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Donahue, J., Darrell, T., & Efros, A. (2016) Context encoders: Feature learning by inpainting. In CVPR.","DOI":"10.1109\/CVPR.2016.278"},{"key":"1336_CR23","unstructured":"Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR."},{"key":"1336_CR24","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016a). Generative adversarial text-to-image synthesis. In ICML."},{"key":"1336_CR25","unstructured":"Reed, S. E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., & Lee, H. (2016b). Learning what and where to draw. In NIPS."},{"key":"1336_CR26","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved techniques for training GANs. In NIPS."},{"key":"1336_CR27","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"1336_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1778765.1778862","volume":"29","author":"K Sunkavalli","year":"2010","unstructured":"Sunkavalli, K., Johnson, M. K., Matusik, W., & Pfister, H. (2010). Multi-scale image harmonization. ACM Transactions on Graphics (TOG), 29, 1\u201310.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1336_CR29","doi-asserted-by":"crossref","unstructured":"Tsai, Y. H., Shen, X., Lin, Z., Sunkavalli, K., Lu, X., & Yang, M. H. (2017). Deep image harmonization. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.299"},{"key":"1336_CR30","doi-asserted-by":"crossref","unstructured":"Wang, T. C., Liu, M. Y., Zhu, J. Y., Tao, A., Kautz, J., & Catanzaro, B. (2017) High-resolution image synthesis and semantic manipulation with conditional GANs. arXiv preprint arXiv:1711.11585.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"1336_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185580","volume":"31","author":"S Xue","year":"2012","unstructured":"Xue, S., Agarwala, A., Dorsey, J., & Rushmeier, H. (2012). Understanding and improving the realism of image composites. ACM Transactions on Graphics (TOG), 31, 1\u201310.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1336_CR32","doi-asserted-by":"crossref","unstructured":"Yang, C., Lu, X., Lin, Z., Shechtman, E., Wang, O., & Li, H. (2017). High-resolution image inpainting using multi-scale neural patch synthesis. In CVPR.","DOI":"10.1109\/CVPR.2017.434"},{"key":"1336_CR33","unstructured":"Yang, J., Kannan, A., Batra, D., & Parikh, D. (2017). LR-GAN: Layered recursive generative adversarial networks for image generation. arXiv preprint arXiv:1703.01560."},{"key":"1336_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Huang, X., Wang, X., & Metaxas, D. (2017). Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV.","DOI":"10.1109\/ICCV.2017.629"},{"key":"1336_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., & Efros, A. A. (2016). Colorful image colorization. In ECCV.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"1336_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tulsiani, S., Sun, W., Malik, J., & Efros, A. A. (2016). View synthesis by appearance flow. In ECCV.","DOI":"10.1007\/978-3-319-46493-0_18"},{"key":"1336_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y., Krahenbuhl, P., Shechtman, E., & Efros, A. A. (2015). Learning a discriminative model for the perception of realism in composite images. In ICCV.","DOI":"10.1109\/ICCV.2015.449"},{"key":"1336_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017a). Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV.","DOI":"10.1109\/ICCV.2017.244"},{"key":"1336_CR39","unstructured":"Zhu, J. Y., Zhang, R., Pathak, D., Darrell, T., Efros, A. A., Wang, O., & Shechtman, E. (2017b). Toward multimodal image-to-image translation. In NIPS."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01336-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-020-01336-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01336-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,27]],"date-time":"2021-05-27T23:42:57Z","timestamp":1622158977000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-020-01336-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,28]]},"references-count":39,"journal-issue":{"issue":"10-11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1336"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01336-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,28]]},"assertion":[{"value":"20 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}