{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:51:14Z","timestamp":1773795074841,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"21-22","license":[{"start":{"date-parts":[[2018,9,25]],"date-time":"2018-09-25T00:00:00Z","timestamp":1537833600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,9,25]],"date-time":"2018-09-25T00:00:00Z","timestamp":1537833600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701463"],"award-info":[{"award-number":["61701463"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010031","name":"Postdoctoral Research Foundation of China","doi-asserted-by":"publisher","award":["2017M622277"],"award-info":[{"award-number":["2017M622277"]}],"id":[{"id":"10.13039\/501100010031","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["201713019"],"award-info":[{"award-number":["201713019"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"crossref","award":["ZR2017BF011"],"award-info":[{"award-number":["ZR2017BF011"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Qingdao Postdoctoral Science Foundation of China"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s11042-018-6694-x","type":"journal-article","created":{"date-parts":[[2018,9,25]],"date-time":"2018-09-25T07:31:48Z","timestamp":1537860708000},"page":"14357-14374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Depth map prediction from a single image with generative adversarial nets"],"prefix":"10.1007","volume":"79","author":[{"given":"Shaoyong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenchen","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4372-1767","authenticated-orcid":false,"given":"Zhibin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,25]]},"reference":[{"key":"6694_CR1","unstructured":"Arjovsky M, Chintala S, Bottou L (2017) Wasserstein gan. arXiv: 1701.07875"},{"key":"6694_CR2","unstructured":"Brock A, Lim T, Ritchie JM, Weston N (2016) Neural photo editing with introspective adversarial networks. arXiv: 1609.07093"},{"key":"6694_CR3","doi-asserted-by":"crossref","unstructured":"Cao Y, Xia Y, Wang Z (2010) A close-form iterative algorithm for depth inferring from a single image. In: European Conference on computer vision. Springer, pp 729\u2013742","DOI":"10.1007\/978-3-642-15555-0_53"},{"key":"6694_CR4","doi-asserted-by":"crossref","unstructured":"Cao Y, Wu Z, Shen C (2017) Estimating depth from monocular images as classification using deep fully convolutional residual networks. IEEE Transactions on Circuits and Systems for Video Technology","DOI":"10.1109\/TCSVT.2017.2740321"},{"key":"6694_CR5","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: Advances in neural information processing systems, pp 2172\u20132180"},{"key":"6694_CR6","doi-asserted-by":"crossref","unstructured":"Cherian A, Morellas V, Papanikolopoulos N (2009) Accurate 3d ground plane estimation from a single image. In: IEEE International conference on robotics and automation, 2009. ICRA\u201909. IEEE, pp 2243\u20132249","DOI":"10.1109\/ROBOT.2009.5152260"},{"key":"6694_CR7","unstructured":"Clayden K (2012) Personality, motivation and level of involvement of land-based recreationists in the Irish uplands. Ph.D. thesis, Waterford Institute of Technology"},{"key":"6694_CR8","doi-asserted-by":"crossref","unstructured":"Dong H, Yu S, Wu C, Guo Y (2017) Semantic image synthesis via adversarial learning. arXiv: 1707.06873","DOI":"10.1109\/ICCV.2017.608"},{"key":"6694_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: Proceedings of the IEEE international conference on computer vision, pp 2650\u20132658","DOI":"10.1109\/ICCV.2015.304"},{"key":"6694_CR10","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems, pp 2366\u20132374"},{"issue":"1","key":"6694_CR11","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1109\/TRO.2013.2279412","volume":"30","author":"F Endres","year":"2014","unstructured":"Endres F, Hess J, Sturm J, Cremers D, Burgard W (2014) 3-d mapping with an rgb-d camera. IEEE Trans Robot 30(1):177\u2013187","journal-title":"IEEE Trans Robot"},{"key":"6694_CR12","unstructured":"Fan X, Zheng K, Lin Y, Wang S (2015) Combining local appearance and holistic view: Dual-source deep neural networks for human pose estimation. arXiv: 1504.07159"},{"issue":"11","key":"6694_CR13","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. Int J Robot Res 32(11):1231\u20131237","journal-title":"Int J Robot Res"},{"key":"6694_CR14","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"6694_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, pp 2672\u20132680"},{"key":"6694_CR16","unstructured":"Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC (2017) Improved training of wasserstein gans. In: Advances in neural information processing systems, pp 5769\u20135779"},{"key":"6694_CR17","unstructured":"Harman PV, Flack J, Fox S, Dowley M (2002) Rapid 2d-to-3d conversion. In: Stereoscopic displays and virtual reality systems IX, vol 4660. International Society for Optics and Photonics, pp 78\u201387"},{"issue":"12","key":"6694_CR18","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1109\/TPAMI.2010.168","volume":"33","author":"K He","year":"2011","unstructured":"He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341\u20132353","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6694_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"6694_CR20","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-008-0137-5","volume":"80","author":"D Hoiem","year":"2008","unstructured":"Hoiem D, Efros AA, Hebert M (2008) Putting objects in perspective. Int J Comput Vis 80(1):3\u201315","journal-title":"Int J Comput Vis"},{"key":"6694_CR21","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu JY, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks arXiv preprint","DOI":"10.1109\/CVPR.2017.632"},{"key":"6694_CR22","unstructured":"Jung JI, Ho YS (2010) Depth map estimation from single-view image using object classification based on bayesian learning. In: 3DTV-conference: the true vision-capture, transmission and display of 3D video (3DTV-CON), 2010. IEEE, pp 1\u20134"},{"key":"6694_CR23","doi-asserted-by":"crossref","unstructured":"Kaneko T, Hiramatsu K, Kashino K (2017) Generative attribute controller with conditional filtered generative adversarial networks. In: IEEE Conference on computer vision and pattern recognition (CVPR), vol 2","DOI":"10.1109\/CVPR.2017.741"},{"key":"6694_CR24","unstructured":"Karacan L, Akata Z, Erdem A, Erdem E (2016) Learning to generate images of outdoor scenes from attributes and semantic layouts. arXiv: 1612.00215"},{"key":"6694_CR25","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"6694_CR26","doi-asserted-by":"crossref","unstructured":"Laina I, Rupprecht C, Belagiannis V, Tombari F, Navab N (2016) Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International conference on 3D vision (3DV). IEEE, pp 239\u2013248","DOI":"10.1109\/3DV.2016.32"},{"key":"6694_CR27","doi-asserted-by":"crossref","unstructured":"Ledig C, Theis L, Husz\u00e1r F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z et al (2016) Photo-realistic single image super-resolution using a generative adversarial network. ArXiv preprint","DOI":"10.1109\/CVPR.2017.19"},{"key":"6694_CR28","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.compeleceng.2016.08.008","volume":"54","author":"Y Li","year":"2016","unstructured":"Li Y, Lu H, Li J, Li X, Li Y, Serikawa S (2016) Underwater image de-scattering and classification by deep neural network. Comput Electric Eng 54:68\u201377","journal-title":"Comput Electric Eng"},{"key":"6694_CR29","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.patcog.2017.11.007","volume":"76","author":"P Li","year":"2018","unstructured":"Li P, Wang D, Wang L, Lu H (2018) Deep visual tracking: review and experimental comparison. Pattern Recogn 76:323\u2013338","journal-title":"Pattern Recogn"},{"key":"6694_CR30","doi-asserted-by":"crossref","unstructured":"Liu B, Gould S, Koller D (2010) Single image depth estimation from predicted semantic labels. In: 2010 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 1253\u20131260","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"6694_CR31","doi-asserted-by":"crossref","unstructured":"Liu F, Shen C, Lin G (2015) Deep convolutional neural fields for depth estimation from a single image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5162\u20135170","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"6694_CR32","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6694_CR33","doi-asserted-by":"crossref","unstructured":"Lu H, Li B, Zhu J, Li Y, Li Y, Xu X, He L, Li X, Li J, Serikawa S (2017) Wound intensity correction and segmentation with convolutional neural networks. Concurr Comput Pract Exper, 29(6)","DOI":"10.1002\/cpe.3927"},{"key":"6694_CR34","doi-asserted-by":"crossref","unstructured":"Lu H, Li Y, Mu S, Wang D, Kim H, Serikawa S (2017) Motor anomaly detection for unmanned aerial vehicles using reinforcement learning. IEEE Internet of Things Journal","DOI":"10.1109\/JIOT.2017.2737479"},{"issue":"2","key":"6694_CR35","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/s11036-017-0932-8","volume":"23","author":"H Lu","year":"2018","unstructured":"Lu H, Li Y, Chen M, Kim H, Serikawa S (2018) Brain intelligence: go beyond artificial intelligence. Mobile Netw Appl 23(2):368\u2013375","journal-title":"Mobile Netw Appl"},{"key":"6694_CR36","doi-asserted-by":"crossref","unstructured":"Lu H, Li Y, Uemura T, Kim H, Serikawa S (2018) Low illumination underwater light field images reconstruction using deep convolutional neural networks. Future Generation Computer Systems","DOI":"10.1016\/j.future.2018.01.001"},{"key":"6694_CR37","doi-asserted-by":"crossref","unstructured":"Mao X, Li Q, Xie H, Lau RY, Wang Z, Smolley SP (2017) Least squares generative adversarial networks. In: 2017 IEEE International conference on computer vision (ICCV). IEEE, pp 2813\u20132821","DOI":"10.1109\/ICCV.2017.304"},{"key":"6694_CR38","unstructured":"Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv: 1511.06434"},{"key":"6694_CR39","doi-asserted-by":"crossref","unstructured":"Roy A, Todorovic S (2016) Monocular depth estimation using neural regression forest. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5506\u20135514","DOI":"10.1109\/CVPR.2016.594"},{"issue":"3","key":"6694_CR40","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"issue":"1","key":"6694_CR41","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s11263-007-0071-y","volume":"76","author":"A Saxena","year":"2008","unstructured":"Saxena A, Chung SH, Ng AY (2008) 3-d depth reconstruction from a single still image. Int J Comput Vis 76(1):53\u201369","journal-title":"Int J Comput Vis"},{"issue":"5","key":"6694_CR42","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2009","unstructured":"Saxena A, Sun M, Ng AY (2009) Make3d: learning 3d scene structure from a single still image. IEEE Trans Pattern Anal Mach Intell 31(5):824\u2013840","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"6694_CR43","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.compeleceng.2013.10.016","volume":"40","author":"S Serikawa","year":"2014","unstructured":"Serikawa S, Lu H (2014) Underwater image dehazing using joint trilateral filter. Comput Electric Eng 40(1):41\u201350","journal-title":"Comput Electric Eng"},{"issue":"11","key":"6694_CR44","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi B, Bai X, Yao C (2017) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans Pattern Anal Mach Intell 39(11):2298\u20132304","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6694_CR45","doi-asserted-by":"crossref","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: European Conference on computer vision. Springer, pp 746\u2013760","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"6694_CR46","unstructured":"S\u00f8nderby CK, Caballero J, Theis L, Shi W, Husz\u00e1r F (2016) Amortised map inference for image super-resolution. arXiv: 1610.04490"},{"key":"6694_CR47","doi-asserted-by":"crossref","unstructured":"Wang P, Shen X, Lin Z, Cohen S, Price B, Yuille AL (2015) Towards unified depth and semantic prediction from a single image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2800\u20132809","DOI":"10.1109\/CVPR.2015.7298897"},{"issue":"3","key":"6694_CR48","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TIP.2016.2521180","volume":"25","author":"Q Wang","year":"2016","unstructured":"Wang Q, Li S, Qin H, Hao A (2016) Super-resolution of multi-observed rgb-d images based on nonlocal regression and total variation. IEEE Trans Image Process 25 (3):1425\u20131440","journal-title":"IEEE Trans Image Process"},{"key":"6694_CR49","unstructured":"Xu X, He L, Lu H, Gao L, Ji Y (2018) Deep adversarial metric learning for cross-modal retrieval. World Wide Web, 1\u201316"},{"key":"6694_CR50","doi-asserted-by":"crossref","unstructured":"Yang W, Zhou Q, Fan Y, Gao G, Wu S, Ou W, Lu H, Cheng J, Latecki LJ (2017) Deep context convolutional neural networks for semantic segmentation. In: CCF Chinese conference on computer vision. Springer, pp 696\u2013704","DOI":"10.1007\/978-981-10-7299-4_58"},{"key":"6694_CR51","doi-asserted-by":"crossref","unstructured":"Yu L, Zhang W, Wang J, Yu Y (2017) Seqgan: sequence generative adversarial nets with policy gradient. In: AAAI, pp 2852\u20132858","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"6694_CR52","doi-asserted-by":"crossref","unstructured":"Zhao W, Zhao F, Wang D, Lu H (2018) Defocus blur detection via multi-stream bottom-top-bottom fully convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3080\u20133088","DOI":"10.1109\/CVPR.2018.00325"},{"key":"6694_CR53","doi-asserted-by":"crossref","unstructured":"Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International conference on computer vision","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6694-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6694-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6694-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T17:22:17Z","timestamp":1662139337000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6694-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,25]]},"references-count":53,"journal-issue":{"issue":"21-22","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["6694"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6694-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,25]]},"assertion":[{"value":"8 June 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}