{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:00:53Z","timestamp":1740171653628,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071287"],"award-info":[{"award-number":["62071287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["20DZ2290100"],"award-info":[{"award-number":["20DZ2290100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Project of Science and Technology of Henan","award":["212102310383"],"award-info":[{"award-number":["212102310383"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The purpose of image composition is to combine the visual elements of different natural images to produce a natural image. The performance of most existing image composition methods drops significantly when they solve multiple issues, such as image harmonization, image blending, shadow generation, object placement, and spatial transformation. To address this problem, we propose a multitask GAN for image compositing based on spatial features, aiming to simultaneously address the geometric and appearance inconsistency. We use three related learning objective functions to train the network. Moreover, a new dataset including 7756 images with RoI region annotations is contributed to help evaluate the multitask image compositing results. Extensive experiments demonstrate that our proposed method is effective on our dataset.<\/jats:p>","DOI":"10.1186\/s13634-023-01009-y","type":"journal-article","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T11:01:47Z","timestamp":1682593307000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MT-GAN: toward realistic image composition based on spatial features"],"prefix":"10.1186","volume":"2023","author":[{"given":"Xiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guowei","family":"Teng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4409-5585","authenticated-orcid":false,"given":"Ping","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai-yan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"1009_CR1","doi-asserted-by":"crossref","unstructured":"W. Cong, J. Zhang, L. Niu, L. Liu, Z. Ling, W. Li, L. Zhang, DoveNet: Deep image harmonization via domain verification.In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"1009_CR2","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1109\/TIP.2020.2975979","volume":"29","author":"X Cun","year":"2020","unstructured":"X. Cun, C. Pun, Improving the harmony of the composite image by spatial-separated attention module. IEEE Trans. Image Process. 29, 759\u20134771 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"1009_CR3","doi-asserted-by":"crossref","unstructured":"Y. Tsai, X. Shen, Z. Lin, K. Sunkavalli, X. Lu, M. Yang, Deep image harmonization.In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.299"},{"key":"1009_CR4","doi-asserted-by":"crossref","unstructured":"H. Wu, S. Zheng, J. Zhang, K. Huang, GP-GAN: Towards realistic high-resolution image blending.the ACM International Conference on Multimedia (2019)","DOI":"10.1145\/3343031.3350944"},{"issue":"3","key":"1009_CR5","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1109\/TIP.2014.2303650","volume":"23","author":"L Zhang","year":"2014","unstructured":"L. Zhang, Y. Gao, R. Zimmermann, Q. Tian, X. Li, Fusion of multichannel local; global structural cues for photo aesthetics evaluation. IEEE Trans. Image Process. 23(3), 419\u20131429 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"1009_CR6","doi-asserted-by":"crossref","unstructured":"D. Liu, C. Long, H. Zhang, H. Yu, X. Dong, C. Xiao, ARshadow-Gan: Shadow generative adversarial network for augmented reality in single light scenes.In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00816"},{"key":"1009_CR7","doi-asserted-by":"crossref","unstructured":"Y. Sheng, J. Zhang, B. Benes, SSN: Soft shadow network for image compositing.In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00436"},{"issue":"1","key":"1009_CR8","doi-asserted-by":"publisher","first-page":"05","DOI":"10.1007\/s41095-019-0136-1","volume":"5","author":"S Zhang","year":"2019","unstructured":"S. Zhang, R. Liang, M. Wang, ShadowGAN: shadow synthesis for virtual objects with conditional adversarial networks. Comput. Visual Media 5(1), 05\u2013115 (2019)","journal-title":"Comput. Visual Media"},{"key":"1009_CR9","doi-asserted-by":"crossref","unstructured":"S. Tripathi, S. Chandra, A. Agrawal, A. Tyagi, J. Rehg, V. Chari, Learning to generate synthetic data via compositing.In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00055"},{"key":"1009_CR10","doi-asserted-by":"crossref","unstructured":"L. Zhang, T. Wen, J. Min, J. Wang, D. Han, J. Shi, Learning object placement by inpainting for compositional data augmentation. The European Conference on Computer Vision(ECCV) (2020)","DOI":"10.1007\/978-3-030-58601-0_34"},{"key":"1009_CR11","doi-asserted-by":"crossref","unstructured":"L. Lin, ST-GAN: spatial transformer generative adversarial networks for image compositing.In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00985"},{"key":"1009_CR12","doi-asserted-by":"crossref","unstructured":"C. Lin, E. Yumer, O. Wang, E. Shechtman, S. Lucey, ST-GAN: spatial transformer generative adversarial networks for image compositing. In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00985"},{"key":"1009_CR13","doi-asserted-by":"crossref","unstructured":"K. Kikuchi, K. Yamaguchi, E. Simo-Serra, T. Kobayashi, Regularized adversarial training for single-shot virtual try-on. The IEEE International Conference on Computer Vision (ICCV) Workshop (2019)","DOI":"10.1109\/ICCVW.2019.00386"},{"key":"1009_CR14","unstructured":"I. Goodfellow, A. Abadie J, M. Mirza, Generative adversarial nets.International Conference on Neural Information Processing Systems 2672\u20132680 (2014)"},{"issue":"10","key":"1009_CR15","first-page":"570","volume":"128","author":"S Azadi","year":"2020","unstructured":"S. Azadi, D. Pathak, S. Ebrahimi, T. Darrell, Compositional GAN: learning image conditional binary composition. Int. J. Comput. Vis. 128(10), 570\u20132585 (2020)","journal-title":"Int. J. Comput. Vis."},{"issue":"9","key":"1009_CR16","doi-asserted-by":"publisher","first-page":"390","DOI":"10.3390\/ijgi8090390","volume":"8","author":"K Zheng","year":"2019","unstructured":"K. Zheng, M. Wei, G. Sun, B. Anas, Using vehicle synthesis generative adversarial networks to improve vehicle detection in remote sensing images. ISPRS Int. J. Geo-Inf 8(9), 390 (2019)","journal-title":"ISPRS Int. J. Geo-Inf"},{"key":"1009_CR17","doi-asserted-by":"crossref","unstructured":"B. Chen, A. Kae, Toward realistic image compositing with adversarial learning. In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00861"},{"key":"1009_CR18","doi-asserted-by":"crossref","unstructured":"T. Lin, M. Maire, S. Belongie, J. Hays, P. Pietro, R. Deva, D. Piotr, C. L. Zitnick, Microsoft COCO: common objects in context. The European Conference on Computer Vision (ECCV) 8693, 740\u2013775 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"2","key":"1009_CR19","doi-asserted-by":"publisher","first-page":"03","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"M. Everingham, G. Van, C. Williams, J. Winn, A. Zisserman, The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 03\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"1009_CR20","doi-asserted-by":"crossref","unstructured":"M. Cordts, M. Omran, S. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, B. Schiele, The cityscapes dataset for semantic urban scene understanding. In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"1009_CR21","doi-asserted-by":"crossref","unstructured":"G. Georgakis, M. Md, Alimoor Reza, Arsalan Mousavian, Phi-Hung Le, and Jana Kosecka. Multiview RGB-D dataset for object instance detection. In Proceedings of the International Conference on 3D Vision (2016)","DOI":"10.1109\/3DV.2016.52"},{"issue":"4","key":"1009_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2601097.2601101","volume":"33","author":"P Laffont","year":"2014","unstructured":"P. Laffont, Z. Ren, X. Tao, C. Qian, J. Hays, Transient attributes for high level understanding and editing of outdoor scenes. ACM Trans. Graph. 33(4), 1\u201311 (2014)","journal-title":"ACM Trans. Graph."},{"key":"1009_CR23","unstructured":"W. Cong, J. Cao, L. Niu, J. Zhang, X. Gao, Z. Tang, L. Zhang, Deep image harmonization by bridging the reality gap. arXiv:2103.17104 (2021)"},{"key":"1009_CR24","unstructured":"M. Jaderberg, K. Simonyan, K. Zisserman, Spatial transformer networks.  Advances in Neural Information Processing Systems 2017\u20132025 (2015)"},{"key":"1009_CR25","doi-asserted-by":"crossref","unstructured":"F. Zhang, H. Zhu, S. Lu. Spatial Fusion GAN for Image Synthesis. In Proceedings of the Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00377"},{"key":"1009_CR26","unstructured":"D. Kingma, J. Ba, Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"1009_CR27","doi-asserted-by":"crossref","unstructured":"J. Zhu, P. Krahenbuhl, E. Shechtman, A. Efros, Learning a discriminative model for the perception of realism in composite images. The IEEE International Conference on Computer Vision 3943\u20133951 (2015)","DOI":"10.1109\/ICCV.2015.449"},{"key":"1009_CR28","doi-asserted-by":"crossref","unstructured":"J. Zhu, T. Park, P. Isola, Unpaired image-to-image translation using cycle-consistent adversarial networks. The IEEE International Conference on Computer Vision 2242\u20132251 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"1009_CR29","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, Deep residual learning for image recognition. In Proceedings of the Computer Vision and Pattern Recognition (CVPR) 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1009_CR30","doi-asserted-by":"crossref","unstructured":"J. Johnson, A. Alahi, L. Fei-Fei, Perceptual losses for real-time style transfer and super-resolution. The European Conference on Computer Vision (ECCV) 694\u2013711 (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"1009_CR31","unstructured":"D. Ulyanov, A. Vedaldi, V. Lempitsky, Instance normalization: the missing ingredient for fast stylization. arXiv: 1607.08022 (2016)"},{"key":"1009_CR32","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"1009_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116489","volume":"99","author":"X Li","year":"2021","unstructured":"X. Li, G. Teng, P. An, H. Yao, Image synthesis via adversarial geometric consistency pursuit. Signal Process.-Image Commun. 99, 116489 (2021)","journal-title":"Signal Process.-Image Commun."},{"key":"1009_CR34","doi-asserted-by":"crossref","unstructured":"Y. Ding, G. Teng, Y. Yao, Context-Aware Natural Integration of Advertisement Object. In Proceedings of the 2019 International Conference on Image Processing 4689\u20134693 (2019)","DOI":"10.1109\/ICIP.2019.8803636"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-023-01009-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13634-023-01009-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-023-01009-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T11:04:16Z","timestamp":1682593456000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-023-01009-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,27]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["1009"],"URL":"https:\/\/doi.org\/10.1186\/s13634-023-01009-y","relation":{},"ISSN":["1687-6180"],"issn-type":[{"type":"electronic","value":"1687-6180"}],"subject":[],"published":{"date-parts":[[2023,4,27]]},"assertion":[{"value":"14 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. All the databases were obtained from the literature that are publicly available.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"46"}}