{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T11:22:16Z","timestamp":1776943336254,"version":"3.51.4"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"7-8","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Open Project of the Key Laboratory of Ministry of Industry and Information Technology for Intelligent Products Testing and Reliability","award":["CEPREI2022-03"],"award-info":[{"award-number":["CEPREI2022-03"]}]},{"name":"Open Project of the Key Laboratory of Ministry of Industry and Information Technology for Intelligent Products Testing and Reliability","award":["CEPREI2022-03"],"award-info":[{"award-number":["CEPREI2022-03"]}]},{"name":"Open Project of the Key Laboratory of Ministry of Industry and Information Technology for Intelligent Products Testing and Reliability","award":["CEPREI2022-03"],"award-info":[{"award-number":["CEPREI2022-03"]}]},{"name":"Open Project of the Key Laboratory of Ministry of Industry and Information Technology for Intelligent Products Testing and Reliability","award":["CEPREI2022-03"],"award-info":[{"award-number":["CEPREI2022-03"]}]},{"name":"Open Project of the Key Laboratory of Ministry of Industry and Information Technology for Intelligent Products Testing and Reliability","award":["CEPREI2022-03"],"award-info":[{"award-number":["CEPREI2022-03"]}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s13042-024-02501-z","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T11:47:51Z","timestamp":1734954471000},"page":"4097-4114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Joint feature modulation mechanism for driving scene image synthesis by instance texture edge and spatial depth priors"],"prefix":"10.1007","volume":"16","author":[{"given":"Yixiang","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huabiao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guancheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"2501_CR1","doi-asserted-by":"crossref","unstructured":"Xu M, Niyato D, Chen J et\u00a0al (2023) Generative AI-empowered simulation for autonomous driving in vehicular mixed reality metaverses. arXiv preprint arXiv:2302.08418","DOI":"10.1109\/JSTSP.2023.3293650"},{"issue":"8","key":"2501_CR2","doi-asserted-by":"publisher","first-page":"13835","DOI":"10.1109\/TITS.2021.3131303","volume":"23","author":"S Saadatnejad","year":"2022","unstructured":"Saadatnejad S, Li S, Mordan T et al (2022) A shared representation for photorealistic driving simulators. IEEE Trans Intell Transp Syst 23(8):13835\u201313845","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"12","key":"2501_CR3","doi-asserted-by":"publisher","first-page":"23114","DOI":"10.1109\/TITS.2022.3193347","volume":"23","author":"E Yurtsever","year":"2022","unstructured":"Yurtsever E, Yang D, Koc IM et al (2022) Photorealism in driving simulations: blending generative adversarial image synthesis with rendering. IEEE Trans Intell Transp Syst 23(12):23114\u201323123","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"2501_CR4","first-page":"1","volume":"4","author":"B Karis","year":"2013","unstructured":"Karis B, Games E (2013) Real shading in unreal engine 4. Proc Phys Based Shading Theory Pract 4(3):1","journal-title":"Proc Phys Based Shading Theory Pract"},{"key":"2501_CR5","doi-asserted-by":"crossref","unstructured":"Yang Z, Chai Y, Anguelov D et\u00a0al (2020) SurfeLGAN: synthesizing realistic sensor data for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11118\u201311127","DOI":"10.1109\/CVPR42600.2020.01113"},{"key":"2501_CR6","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M et\u00a0al (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u20132680"},{"issue":"2","key":"2501_CR7","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/JSAC.2022.3227027","volume":"41","author":"Z Xiao","year":"2022","unstructured":"Xiao Z, Shu J, Jiang H et al (2022) Perception task offloading with collaborative computation for autonomous driving. IEEE J Select Areas Commun 41(2):457\u2013473","journal-title":"IEEE J Select Areas Commun"},{"key":"2501_CR8","doi-asserted-by":"crossref","unstructured":"Park T, Liu MY, Wang TC et\u00a0al (2019) Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2337\u20132346","DOI":"10.1109\/CVPR.2019.00244"},{"key":"2501_CR9","doi-asserted-by":"crossref","unstructured":"Lv Z, Li X, Niu Z et\u00a0al (2022) Semantic-shape adaptive feature modulation for semantic image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11214\u201311223","DOI":"10.1109\/CVPR52688.2022.01093"},{"issue":"2","key":"2501_CR10","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1109\/TPAMI.2022.3161985","volume":"45","author":"G Pu","year":"2023","unstructured":"Pu G, Men Y, Mao Y et al (2023) Controllable image synthesis with attribute-decomposed GAN. IEEE Trans Pattern Anal Mach Intell 45(2):1514\u20131532","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR11","unstructured":"Lee G, Yim J, Kim C et\u00a0al (2022) StyLandGAN: a StyleGAN based landscape image synthesis using depth-map. arXiv preprint arXiv:2205.06611"},{"key":"2501_CR12","doi-asserted-by":"crossref","unstructured":"Musat V, De\u00a0Martini D, Gadd M et\u00a0al (2022) Depth-SIMS: semi-parametric image and depth synthesis. In: Proceedings of 2022 international conference on robotics and automation, pp 2388\u20132394","DOI":"10.1109\/ICRA46639.2022.9811569"},{"issue":"3","key":"2501_CR13","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl R, Lasinger K, Hafner D et al (2020) Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans Pattern Anal Mach Intell 44(3):1623\u20131637","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"10","key":"2501_CR14","doi-asserted-by":"publisher","first-page":"4818","DOI":"10.1109\/TIP.2017.2718185","volume":"26","author":"Z Ni","year":"2017","unstructured":"Ni Z, Ma L, Zeng H et al (2017) ESIM: edge similarity for screen content image quality assessment. IEEE Trans Image Process 26(10):4818\u20134831","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"2501_CR15","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679\u2013698","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"2501_CR16","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/TPAMI.2022.3155989","volume":"45","author":"H Tang","year":"2023","unstructured":"Tang H, Shao L, Torr PH et al (2023) Local and global GANs with semantic-aware upsampling for image generation. IEEE Trans Pattern Anal Mach Intell 45(1):768\u2013784","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"2501_CR17","doi-asserted-by":"publisher","first-page":"14435","DOI":"10.1109\/TPAMI.2023.3298721","volume":"45","author":"H Tang","year":"2023","unstructured":"Tang H, Sun G, Sebe N et al (2023) Edge guided GANs with multi-scale contrastive learning for semantic image synthesis. IEEE Trans Pattern Anal Mach Intell 45(12):14435\u201314452","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR18","doi-asserted-by":"crossref","unstructured":"Shi Y, Liu X, Wei Y et\u00a0al (2022) Retrieval-based spatially adaptive normalization for semantic image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11224\u201311233","DOI":"10.1109\/CVPR52688.2022.01094"},{"key":"2501_CR19","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S et\u00a0al (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"2501_CR20","doi-asserted-by":"crossref","unstructured":"Zhou B, Zhao H, Puig X et\u00a0al (2017) Scene parsing through ade20k dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 633\u2013641","DOI":"10.1109\/CVPR.2017.544"},{"key":"2501_CR21","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu JY, Zhou T et\u00a0al (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"2501_CR22","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784"},{"key":"2501_CR23","doi-asserted-by":"crossref","unstructured":"Wang TC, Liu MY, Zhu JY et\u00a0al (2018) High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8798\u20138807","DOI":"10.1109\/CVPR.2018.00917"},{"key":"2501_CR24","unstructured":"Liu X, Yin G, Shao J et\u00a0al (2019) Learning to predict layout-to-image conditional convolutions for semantic image synthesis. In: Advances in neural information processing systems, pp 568\u2013578"},{"key":"2501_CR25","doi-asserted-by":"crossref","unstructured":"Wang Y, Qi L, Chen YC et\u00a0al (2021) Image synthesis via semantic composition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13,749\u201313,758","DOI":"10.1109\/ICCV48922.2021.01349"},{"issue":"9","key":"2501_CR26","first-page":"4852","volume":"44","author":"Z Tan","year":"2021","unstructured":"Tan Z, Chen D, Chu Q et al (2021) Efficient semantic image synthesis via class-adaptive normalization. IEEE Trans Pattern Anal Mach Intell 44(9):4852\u20134866","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR27","unstructured":"Sushko V, Sch\u00f6nfeld E, Zhang D et\u00a0al (2021) You only need adversarial supervision for semantic image synthesis. In: Proceedings of 9th international conference on learning representations"},{"key":"2501_CR28","doi-asserted-by":"crossref","unstructured":"Xu M, Lee J, Yoon S et\u00a0al (2023) Variation-aware semantic image synthesis. arXiv preprint arXiv:2301.10551","DOI":"10.1016\/j.imavis.2024.104914"},{"key":"2501_CR29","unstructured":"Wang W, Bao J, Zhou W et\u00a0al (2022) Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050"},{"key":"2501_CR30","doi-asserted-by":"crossref","unstructured":"Park M, Yun J, Choi S et\u00a0al (2023) Learning to generate semantic layouts for higher text-image correspondence in text-to-image synthesis. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7591\u20137600","DOI":"10.1109\/ICCV51070.2023.00698"},{"key":"2501_CR31","doi-asserted-by":"crossref","unstructured":"Mou C, Wang X, Xie L et\u00a0al (2023) T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"2501_CR32","unstructured":"Kingma D, Welling M (2014) Auto-encoding variational Bayes. In: Proceedings of 2nd international conference on learning representations"},{"key":"2501_CR33","doi-asserted-by":"crossref","unstructured":"Zhu P, Abdal R, Qin Y et\u00a0al (2020) SEAN: image synthesis with semantic region-adaptive normalization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5103\u20135112","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"2501_CR34","doi-asserted-by":"crossref","unstructured":"Qi X, Chen Q, Jia J et\u00a0al (2018) Semi-parametric image synthesis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8808\u20138816","DOI":"10.1109\/CVPR.2018.00918"},{"key":"2501_CR35","doi-asserted-by":"crossref","unstructured":"Li Y, Cheng Y, Gan Z et\u00a0al (2020) BachGAN: high-resolution image synthesis from salient object layout. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8365\u20138374","DOI":"10.1109\/CVPR42600.2020.00839"},{"issue":"9","key":"2501_CR36","first-page":"5070","volume":"44","author":"W Sun","year":"2021","unstructured":"Sun W, Wu T (2021) Learning layout and style reconfigurable GANs for controllable image synthesis. IEEE Trans Pattern Anal Mach Intell 44(9):5070\u20135087","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"2501_CR37","first-page":"6247","volume":"45","author":"Z Tan","year":"2023","unstructured":"Tan Z, Chu Q, Chai M et al (2023) Semantic probability distribution modeling for diverse semantic image synthesis. IEEE Trans Pattern Anal Mach Intell 45(5):6247\u20136264","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR38","doi-asserted-by":"crossref","unstructured":"Kong Z, Zhang Y, Yang T et\u00a0al (2024) Omg: Occlusion-friendly personalized multi-concept generation in diffusion models. arXiv preprint arXiv:2403.10983","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"2501_CR39","doi-asserted-by":"crossref","unstructured":"Zhu Z, Xu Z, You A et\u00a0al (2020) Semantically multi-modal image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5467\u20135476","DOI":"10.1109\/CVPR42600.2020.00551"},{"key":"2501_CR40","first-page":"1","volume":"61","author":"P Han","year":"2023","unstructured":"Han P, Zhao B, Li X (2023) Edge-guided remote sensing image compression. IEEE Trans Geosci Remote Sens 61:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2501_CR41","doi-asserted-by":"crossref","unstructured":"Nazeri K, Ng E, Joseph T et\u00a0al (2019) EdgeConnect: structure guided image inpainting using edge prediction. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops, pp 3265\u20133274","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"2501_CR42","doi-asserted-by":"crossref","unstructured":"Huang HP, Tseng HY, Lee HY et\u00a0al (2020) Semantic view synthesis. In: Proceedings of the European conference on computer vision (ECCV). Springer, pp 592\u2013608","DOI":"10.1007\/978-3-030-58610-2_35"},{"issue":"103","key":"2501_CR43","first-page":"135","volume":"203","author":"T Wang","year":"2021","unstructured":"Wang T, Zhang X, Jiang R et al (2021) Video deblurring via spatiotemporal pyramid network and adversarial gradient prior. Comput Vis Image Underst 203(103):135","journal-title":"Comput Vis Image Underst"},{"key":"2501_CR44","doi-asserted-by":"publisher","first-page":"9209","DOI":"10.1109\/TCSVT.2023.3268217","volume":"34","author":"X Zhang","year":"2023","unstructured":"Zhang X, Xu Y, Wang T et al (2023) Multi-prior driven network for RGB-D salient object detection. IEEE Trans Circuits Syst Video Technol 34:9209\u20139222","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2501_CR45","doi-asserted-by":"publisher","first-page":"8494","DOI":"10.1109\/TCSVT.2024.3383659","volume":"34","author":"X Chen","year":"2024","unstructured":"Chen X, Tan J, Wang T et al (2024) Towards real-world blind face restoration with generative diffusion prior. IEEE Trans Circuits Syst Video Technol 34:8494\u20138508","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2501_CR46","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TIP.2024.3393365","volume":"33","author":"L Bao","year":"2024","unstructured":"Bao L, Zhou X, Lu X et al (2024) Quality-aware selective fusion network for V-D-T salient object detection. IEEE Trans Image Process 33:3212\u20133226","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"2501_CR47","doi-asserted-by":"publisher","first-page":"4741","DOI":"10.1109\/TCE.2024.3390841","volume":"70","author":"C Lv","year":"2024","unstructured":"Lv C, Zhou X, Wan B et al (2024) Transformer-based cross-modal integration network for RGB-T salient object detection. IEEE Trans Consum Electron 70(2):4741\u20134755","journal-title":"IEEE Trans Consum Electron"},{"key":"2501_CR48","doi-asserted-by":"publisher","first-page":"7114","DOI":"10.1109\/TMM.2024.3360710","volume":"26","author":"X Zhou","year":"2024","unstructured":"Zhou X, Wu Z, Cong R (2024) Decoupling and integration network for camouflaged object detection. IEEE Trans Multimedia 26:7114\u20137129","journal-title":"IEEE Trans Multimedia"},{"issue":"12","key":"2501_CR49","doi-asserted-by":"publisher","first-page":"7696","DOI":"10.1109\/TCSVT.2023.3278410","volume":"33","author":"X Zhou","year":"2023","unstructured":"Zhou X, Wu S, Shi R et al (2023) Transformer-based multi-scale feature integration network for video saliency prediction. IEEE Trans Circuits Syst Video Technol 33(12):7696\u20137707","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2501_CR50","unstructured":"Yang L, Kang B, Huang Z et\u00a0al (2024) Depth anything v2. arXiv preprint arXiv:2406.09414"},{"issue":"12","key":"2501_CR51","doi-asserted-by":"publisher","first-page":"14956","DOI":"10.1109\/TPAMI.2023.3300513","volume":"45","author":"Z Su","year":"2023","unstructured":"Su Z, Zhang J, Wang L et al (2023) Lightweight pixel difference networks for efficient visual representation learning. IEEE Trans Pattern Anal Mach Intell 45(12):14956\u201314974","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR52","unstructured":"Li Y, Wang Y, Lu Z et\u00a0al (2022) DepthGAN: GAN-based depth generation of indoor scenes from semantic layouts. arXiv preprint arXiv:2203.11453"},{"key":"2501_CR53","doi-asserted-by":"crossref","unstructured":"Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision, pp 1501\u20131510","DOI":"10.1109\/ICCV.2017.167"},{"issue":"1","key":"2501_CR54","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/TIP.2017.2760518","volume":"27","author":"S Bosse","year":"2017","unstructured":"Bosse S, Maniry D, M\u00fcller KR et al (2017) Deep neural networks for no-reference and full-reference image quality assessment. IEEE Trans Image Process 27(1):206\u2013219","journal-title":"IEEE Trans Image Process"},{"key":"2501_CR55","doi-asserted-by":"crossref","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of the European conference on computer vision (ECCV), pp 694\u2013711","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"2501_CR56","unstructured":"Paszke A, Gross S et\u00a0al (2019) PyTorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp 8024\u20138035"},{"key":"2501_CR57","unstructured":"Miyato T, Kataoka T, Koyama M et\u00a0al (2018) Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957"},{"issue":"5","key":"2501_CR58","first-page":"6055","volume":"45","author":"H Tang","year":"2023","unstructured":"Tang H, Torr PH, Sebe N (2023) Multi-channel attention selection GANs for guided image-to-image translation. IEEE Trans Pattern Anal Mach Intell 45(5):6055\u20136071","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR59","doi-asserted-by":"crossref","unstructured":"Tan Z, Chai M, Chen D et\u00a0al (2021) Diverse semantic image synthesis via probability distribution modeling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7962\u20137971","DOI":"10.1109\/CVPR46437.2021.00787"},{"issue":"2","key":"2501_CR60","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller H (2007) Stereo processing by semiglobal matching and mutual information. IEEE Trans Pattern Anal Mach Intell 30(2):328\u2013341","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2501_CR61","unstructured":"Sobel I, Feldman G et\u00a0al (1968) A 3x3 isotropic gradient operator for image processing. A talk at the Stanford Artificial Project in 1968, pp 271\u2013272"},{"key":"2501_CR62","doi-asserted-by":"crossref","unstructured":"Hou X, Zhang L (2007) Saliency detection: a spectral residual approach. In: 2007 IEEE conference on computer vision and pattern recognition. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383267"},{"key":"2501_CR63","doi-asserted-by":"crossref","unstructured":"Zhu Z, Fan Z, Jiang Y et\u00a0al (2025) FSGS: real-time few-shot view synthesis using gaussian splatting. In: European conference on computer vision, pp 145\u2013163","DOI":"10.1007\/978-3-031-72933-1_9"},{"key":"2501_CR64","first-page":"1","volume":"62","author":"P Han","year":"2023","unstructured":"Han P, Zhao B, Li X (2023) Progressive feature interleaved fusion network for remote-sensing image salient object detection. IEEE Trans Geosci Remote Sens 62:1\u201314","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2501_CR65","doi-asserted-by":"publisher","first-page":"2077","DOI":"10.1007\/s13042-020-01098-3","volume":"11","author":"Y Fan","year":"2020","unstructured":"Fan Y, Shao M, Zuo W et al (2020) Unsupervised image-to-image translation using intra-domain reconstruction loss. Int J Mach Learn Cybern 11:2077\u20132088","journal-title":"Int J Mach Learn Cybern"},{"issue":"3","key":"2501_CR66","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/s13042-022-01659-8","volume":"14","author":"H Xu","year":"2023","unstructured":"Xu H, Long X, Wang M (2023) UUGAN: a GAN-based approach towards underwater image enhancement using non-pairwise supervision. Int J Mach Learn Cybern 14(3):725\u2013738","journal-title":"Int J Mach Learn Cybern"},{"key":"2501_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13042-023-01844-3","volume":"14","author":"X Huo","year":"2023","unstructured":"Huo X, Jiang B, Hu H et al (2023) OSAGGAN: one-shot unsupervised image-to-image translation using attention-guided generative adversarial networks. Int J Mach Learn Cybern 14:1\u201312","journal-title":"Int J Mach Learn Cybern"},{"issue":"2","key":"2501_CR68","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/s13042-022-01552-4","volume":"14","author":"P Liu","year":"2023","unstructured":"Liu P, Wang Y, Du A et al (2023) Disentangling latent space better for few-shot image-to-image translation. Int J Mach Learn Cybern 14(2):419\u2013427","journal-title":"Int J Mach Learn Cybern"},{"issue":"1","key":"2501_CR69","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall B, Srinivasan PP, Tancik M et al (2021) NERF: representing scenes as neural radiance fields for view synthesis. Commun ACM 65(1):99\u2013106","journal-title":"Commun ACM"},{"key":"2501_CR70","doi-asserted-by":"crossref","unstructured":"Kundu A, Genova K, Yin X et\u00a0al (2022) Panoptic neural fields: a semantic object-aware neural scene representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12871\u201312881","DOI":"10.1109\/CVPR52688.2022.01253"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02501-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02501-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02501-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T02:27:06Z","timestamp":1757125626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02501-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":70,"journal-issue":{"issue":"7-8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2501"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02501-z","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,23]]},"assertion":[{"value":"11 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}