{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T14:26:41Z","timestamp":1788964001361,"version":"build-2803163510"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T00:00:00Z","timestamp":1743724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T00:00:00Z","timestamp":1743724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["20BKG031"],"award-info":[{"award-number":["20BKG031"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The digitization of ancient murals is crucial in preserving, inheriting, and utilizing cultural heritage. Due to the vast coverage of murals, digitization typically involves capturing images in segments and then stitching them together. However, existing image stitching techniques face limitations regarding efficiency, generalization capabilities, and robustness, which hinder their practical applicability. To solve these problems and improve the performance of image stitching, this paper proposes an unsupervised hierarchical grid-constrained fusion network model. This model consists of two main modules: image alignment and image synthesis. The image alignment module incorporates prior knowledge, such as feature pyramids, attention mechanisms, and context dependencies, to facilitate feature extraction. It also includes a multi-scale grid homography generation part that utilizes region masks to create a deformation field. Additionally, a stitching-domain transformation unit is employed to ensure spatial consistency by deforming the input reference and target images. In the image synthesis module, a progressive inference fusion network framework is proposed to simplify the complex image fusion problem into a multi-granularity image synthesis problem. This framework utilizes two encoder-decoder cascaded network units to merge information progressively from coarse to fine granularity, producing high-resolution stitched images. Experimental results demonstrate that the proposed model exhibits superior robustness on both public and custom image datasets, and generally outperforms state-of-the-art image stitching methods, especially in subjective visual assessments.<\/jats:p>","DOI":"10.1007\/s44443-025-00005-6","type":"journal-article","created":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T16:46:50Z","timestamp":1743871610000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical grid-constrained fusion network for image stitching"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2873-3674","authenticated-orcid":false,"given":"Yongqin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baojie","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linge","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangjiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsheng","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Bay H, Tuytelaars T, Van Gool L (2006) SURF: Speeded up robust features. In: Proceedings of the european conference on computer vision, pp 404\u2013417","DOI":"10.1007\/11744023_32"},{"key":"5_CR2","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s11263-006-0002-3","volume":"74","author":"M Brown","year":"2007","unstructured":"Brown M, Lowe DG (2007) Automatic panoramic image stitching using invariant features. Int J Comput Vis 74:59\u201373","journal-title":"Int J Comput Vis"},{"issue":"9","key":"5_CR3","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.3390\/rs16091483","volume":"16","author":"J Chen","year":"2024","unstructured":"Chen J, Luo Y, Wang J, Tang H, Tang Y, Li J (2024) Elimination of irregular boundaries and seams for uav image stitching with a diffusion model. Remote Sens 16(9):1483","journal-title":"Remote Sens"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"D\u2019Amicantonio G, Bondarev E (2024) Automated camera calibration via homography estimation with gnns. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 5876\u20135883","DOI":"10.1109\/WACV57701.2024.00577"},{"key":"5_CR5","unstructured":"DeTone D, Malisiewicz T, Rabinovich A (2016) Deep image homography estimation. arXiv:1606.03798"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Du P, Ning J, Cui J, Huang S, Wang X, Wang J (2022) Geometric structure preserving warp for natural image stitching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3678\u20133686","DOI":"10.1109\/CVPR52688.2022.00367"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Gao J, Kim SJ, Brown MS (2011) Constructing image panoramas using dual-homography warping. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 49\u201356","DOI":"10.1109\/CVPR.2011.5995433"},{"key":"5_CR8","doi-asserted-by":"publisher","first-page":"111929","DOI":"10.1016\/j.asoc.2024.111929","volume":"164","author":"Y Guo","year":"2024","unstructured":"Guo Y, Zamri NE, Kasihmuddin MSM, Alway A, Mansor MA, Li J, Zhang Q (2024) Dual optimization approach in discrete hopfield neural network. Appl Soft Comput 164:111929","journal-title":"Appl Soft Comput"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Jia Q, Feng X, Liu Y, Fan X, Latecki LJ (2023) Learning pixel-wise alignment for unsupervised image stitching. In: Proceedings of the ACM international conference on multimedia, pp 1392\u20131400","DOI":"10.1145\/3581783.3612298"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Jia Q, Li Z, Fan X, Zhao H (2021) Leveraging line-point consistence to preserve structures for wide parallax image stitching. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12186\u201312195","DOI":"10.1109\/CVPR46437.2021.01201"},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"4288","DOI":"10.1109\/TIP.2024.3430532","volume":"33","author":"Z Jiang","year":"2024","unstructured":"Jiang Z, Zhang Z, Liu J, Fan X, Liu R (2024) Multispectral image stitching via global-aware quadrature pyramid regression. IEEE Trans Image Process 33:4288\u20134302","journal-title":"IEEE Trans Image Process"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Kim M, Lee J, Lee B, Im S, Jin KH (2024) Implicit neural image stitching with enhanced and blended feature reconstruction. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 4075\u20134084","DOI":"10.1109\/WACV57701.2024.00404"},{"key":"5_CR13","unstructured":"Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: Proceedings of the international conference on learning representations, pp 1\u201315"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Kweon H, Kim H, Kang Y, Yoon Y, Jeong W, Yoon KJ (2023) Pixel-wise warping for deep image stitching. In: Proceedings of the AAAI conference on artificial intelligence, pp 1196\u20131204","DOI":"10.1609\/aaai.v37i1.25202"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Le H, Liu F, Zhang S, Agarwala A (2020) Deep homography estimation for dynamic scenes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7649\u20137658","DOI":"10.1109\/CVPR42600.2020.00767"},{"issue":"7","key":"5_CR16","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1109\/TMM.2017.2777461","volume":"20","author":"J Li","year":"2018","unstructured":"Li J, Wang Z, Lai S, Zhai Y, Zhang M (2018) Parallax-tolerant image stitching based on robust elastic warping. IEEE Trans Multim 20(7):1672\u20131687","journal-title":"IEEE Trans Multim"},{"key":"5_CR17","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1109\/TIP.2019.2934344","volume":"29","author":"T Liao","year":"2020","unstructured":"Liao T, Li N (2020) Single-perspective warps in natural image stitching. IEEE Trans Image Process 29:724\u2013735","journal-title":"IEEE Trans Image Process"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Lin WY, Liu S, Matsushita Y, Ng TT, Cheong LF (2011) Smoothly varying affine stitching. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 345\u2013352","DOI":"10.1109\/CVPR.2011.5995314"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Lin K, Jiang N, Cheong LF, Do MN, Lu J (2016) SEAGULL: Seam-guided local alignment for parallax-tolerant image stitching. In: Proceedings of the european conference on computer vision, pp 370\u2013385","DOI":"10.1007\/978-3-319-46487-9_23"},{"issue":"3","key":"5_CR20","first-page":"2849","volume":"45","author":"S Liu","year":"2023","unstructured":"Liu S, Ye N, Wang C, Zhang J, Jia L, Luo K, Wang J, Sun J (2023) Content-aware unsupervised deep homography estimation and its extensions. IEEE Trans Pattern Anal Mach Intell 45(3):2849\u20132863","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91\u2013110","journal-title":"Int J Comput Vis"},{"issue":"1","key":"5_CR22","doi-asserted-by":"publisher","first-page":"9215","DOI":"10.1038\/s41598-024-59626-y","volume":"14","author":"FS Mohammadi","year":"2024","unstructured":"Mohammadi FS, Mohammadi SE, Mojarad Adi P, Mirkarimi SMA, Shabani H (2024) A comparative analysis of pairwise image stitching techniques for microscopy images. SCI REP-UK 14(1):9215","journal-title":"SCI REP-UK"},{"issue":"3","key":"5_CR23","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1109\/LRA.2018.2809549","volume":"3","author":"T Nguyen","year":"2018","unstructured":"Nguyen T, Chen SW, Shivakumar SS, Taylor CJ, Kumar V (2018) Unsupervised deep homography: A fast and robust homography estimation model. IEEE Robotics Autom Lett 3(3):2346\u20132353","journal-title":"IEEE Robotics Autom Lett"},{"key":"5_CR24","doi-asserted-by":"publisher","first-page":"102950","DOI":"10.1016\/j.jvcir.2020.102950","volume":"73","author":"L Nie","year":"2020","unstructured":"Nie L, Lin C, Liao K, Liu M, Zhao Y (2020) A view-free image stitching network based on global homography. J Vis Commun Image Represent 73:102950","journal-title":"J Vis Commun Image Represent"},{"key":"5_CR25","doi-asserted-by":"publisher","first-page":"6184","DOI":"10.1109\/TIP.2021.3092828","volume":"30","author":"L Nie","year":"2021","unstructured":"Nie L, Lin C, Liao K, Liu S, Zhao Y (2021) Unsupervised deep image stitching: Reconstructing stitched features to images. IEEE Trans Image Process 30:6184\u20136197","journal-title":"IEEE Trans Image Process"},{"key":"5_CR26","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/j.neucom.2021.12.032","volume":"491","author":"L Nie","year":"2022","unstructured":"Nie L, Lin C, Liao K, Zhao Y (2022a) Learning edge-preserved image stitching from multi-scale deep homography. Neurocomputing 491:533\u2013543","journal-title":"Neurocomputing"},{"issue":"7","key":"5_CR27","doi-asserted-by":"publisher","first-page":"4460","DOI":"10.1109\/TCSVT.2021.3125736","volume":"32","author":"L Nie","year":"2022","unstructured":"Nie L, Lin C, Liao K, Liu S, Zhao Y (2022b) Depth-aware multi-grid deep homography estimation with contextual correlation. IEEE Trans Circuits Syst Video Technol 32(7):4460\u20134472","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Nie L, Lin C, Liao K, Liu S, Zhao Y (2023) Parallax-tolerant unsupervised deep image stitching. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7365\u20137374","DOI":"10.1109\/ICCV51070.2023.00680"},{"issue":"2","key":"5_CR29","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1007\/s00521-022-07806-0","volume":"35","author":"X Peng","year":"2023","unstructured":"Peng X, Zhao H, Wang X, Zhang Y, Li Z, Zhang Q, Wang J, Peng J, Liang H (2023) C3n: content-constrained convolutional network for mural image completion. Neural Comput Appl 35(2):1959\u20131970","journal-title":"Neural Comput Appl"},{"key":"5_CR30","unstructured":"Pogorelyuk L, Radev ST (2024) Aligning motion-blurred images using contrastive learning on overcomplete pixels. arXiv:2410.07410"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Proceedings of the international conference on medical image computing and computer-assisted intervention, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"5","key":"5_CR32","doi-asserted-by":"publisher","first-page":"101554","DOI":"10.1016\/j.jksuci.2023.101554","volume":"35","author":"NA Rusdi","year":"2023","unstructured":"Rusdi NA, Kasihmuddin MSM, Romli NA, Manoharam G, Mansor MA (2023) Multi-unit discrete hopfield neural network for higher order supervised learning through logic mining: Optimal performance design and attribute selection. J King Saud Univ Comput Inf Sci 35(5):101554","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"5_CR33","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/s11265-019-01477-2","volume":"92","author":"Z Shi","year":"2020","unstructured":"Shi Z, Li H, Cao Q, Ren H, Fan B (2020) An image mosaic method based on convolutional neural network semantic features extraction. J Signal Process Syst 92:435\u2013444","journal-title":"J Signal Process Syst"},{"key":"5_CR34","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"issue":"4","key":"5_CR35","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/s00530-020-00651-y","volume":"26","author":"Z Wang","year":"2020","unstructured":"Wang Z, Yang Z (2020) Review on image-stitching techniques. Multim Syst 26(4):413\u2013430","journal-title":"Multim Syst"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Wei Z, Lan C, Xu Q, Wang L, Gao T, Yao F, Hou H (2024) Satellstitch: Satellite imagery-assisted uav image seamless stitching for emergency response without gcp and gnss. Remote Sens 16(2):309","DOI":"10.3390\/rs16020309"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Xiao J, Guo H, Zhou J, Zhao T, Yu Q, Chen Y, Wang Z (2023) Tiny object detection with context enhancement and feature purification. Expert Syst Appl 211:118665","DOI":"10.1016\/j.eswa.2022.118665"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Xiao J, Wang S, Zhou J, Tian Z, Zhang H, Wang Y.-F (2024) Mim: High-definition maps incorporated multi-view 3d object detection. IEEE Trans Intell Transp Syst, 10\u2013110920243520814","DOI":"10.1109\/TITS.2024.3520814"},{"issue":"4","key":"5_CR39","doi-asserted-by":"publisher","first-page":"3863","DOI":"10.1007\/s11063-023-11226-z","volume":"55","author":"N Yan","year":"2023","unstructured":"Yan N, Mei Y, Xu L, Yu H, Sun B, Wang Z, Chen Y (2023) Deep learning on image stitching with multi-viewpoint images: A survey. Neural Process Lett 55(4):3863\u20133898","journal-title":"Neural Process Lett"},{"key":"5_CR40","unstructured":"Ye N, Wang C, Liu S, Jia L, Wang J, Cui Y (2019) DeepMeshFlow: Content adaptive mesh deformation for robust image registration. arXiv:1912.05131"},{"key":"5_CR41","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1016\/j.compeleceng.2016.11.034","volume":"62","author":"HN Zahra","year":"2017","unstructured":"Zahra HN, Nasri M (2017) An adaptive image registration method based on sift features and ransac transform. Comput Electr Eng 62:524\u2013537","journal-title":"Comput Electr Eng"},{"issue":"7","key":"5_CR42","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TPAMI.2013.247","volume":"36","author":"J Zaragoza","year":"2014","unstructured":"Zaragoza J, Chin TJ, Tran QH, Brown MS, Suter D (2014) As-projective-as-possible image stitching with moving DLT. IEEE Trans Pattern Anal Mach Intell 36(7):1285\u20131298","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"5_CR43","doi-asserted-by":"publisher","first-page":"23519","DOI":"10.1038\/s41598-024-72368-1","volume":"14","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Wang X, Zhu P, Lu X, Xiao J, Zhou W, Li Z, Peng X (2024a) Prn: progressive reasoning network and its image completion applications. SCI REP-UK 14(1):23519","journal-title":"SCI REP-UK"},{"issue":"4","key":"5_CR44","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1007\/s41095-024-0420-6","volume":"10","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Lai YK, Nie L, Zhang FL, Xu L (2024b) Recstitchnet: Learning to stitch images with rectangular boundaries. Comput Vis Media 10(4):687\u2013703","journal-title":"Comput Vis Media"},{"issue":"3","key":"5_CR45","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1109\/TCSVT.2021.3068761","volume":"32","author":"X Zhao","year":"2022","unstructured":"Zhao X, Liu J, Wu X, Chen W, Guo F, Li Z (2022) Probabilistic spatial distribution prior based attentional keypoints matching network. IEEE Trans Circuits Syst Video Technol 32(3):1313\u20131327","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Zhou T, Li H, Wang Z, Luo A, Zhang C.L, Li J, Zeng B, Liu S (2024) Recdiffusion: Rectangling for image stitching with diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2692\u20132701","DOI":"10.1109\/CVPR52733.2024.00260"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Zhuang B, Tran QH (2020) Image stitching and rectification for hand-held cameras. In: Proceedings of the European conference on computer vision, pp 243\u2013260","DOI":"10.1007\/978-3-030-58571-6_15"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00005-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-025-00005-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00005-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T11:45:36Z","timestamp":1748605536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-025-00005-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,4]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["5"],"URL":"https:\/\/doi.org\/10.1007\/s44443-025-00005-6","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,4]]},"assertion":[{"value":"10 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2025","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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Written informed consent for publication was obtained from all participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"Our code and results will be publicly accessible at .","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code Availability"}}],"article-number":"17"}}