{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T12:14:05Z","timestamp":1785413645565,"version":"3.56.0"},"reference-count":34,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"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":["61971201"],"award-info":[{"award-number":["61971201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["61971201"],"award-info":[{"award-number":["61971201"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Key Research Project in Priority Areas of Guangdong Provincial Universities","award":["2025ZDZX1002"],"award-info":[{"award-number":["2025ZDZX1002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Image stitching is a computational technique designed to align and seamlessly fuse multiple overlapping images into a single panoramic image with an extended field of view. It plays a critical role in diverse domains, including mobile photography, autonomous navigation, and visual perception systems. However, most conventional image stitching pipelines implicitly assume that the input images have been pre-corrected for geometric distortions, particularly radial distortion inherent to wide-angle and fisheye lenses. This assumption often fails in practice, as many consumer-grade cameras lack built-in correction or calibration support. Consequently, applying standard image stitching methods to the uncorrected imagery frequently degrades feature correspondence reliability and introduces visible geometric misalignments and seam discontinuities in the final panorama. To overcome these limitations, this paper introduces a task-driven joint iterative optimization framework for image stitching that unifies unsupervised radial distortion correction, distortion-aware feature registration, and seam-aware blending within a single cohesive optimization objective. Specifically, lens distortion parameters are explicitly modeled as learnable variables and embedded into both the geometric registration and seam optimization sub-problems. An efficient closed-loop optimization strategy is then employed to jointly refine distortion parameters, homography estimates, and optimal seam paths in an alternating, mutually reinforcing manner. Implementation-wise, we first propose a calibration-free initial radial distortion estimation method which leverages intrinsic image gradients and epipolar consistency to provide physically plausible initialization for subsequent optimization. During iteration, distortion parameters are progressively refined by integrating robust geometric constraints derived from current feature matches (via RANSAC-based consensus filtering) with photometric consistency cues. Extensive experiments on multiple public benchmarks featuring pronounced radial distortion demonstrate that our method achieves superior stitching fidelity using metrics including PSNR and SSIM. It also confirms enhanced feature matching stability, which outperforms both distortion-agnostic approaches and two-stage pipelines that decouple distortion correction from registration. Furthermore, comprehensive ablation studies quantitatively and qualitatively validate the functional necessity and synergistic contribution of each core module, confirming the design rationale and effectiveness of the proposed joint optimization architecture.<\/jats:p>","DOI":"10.3390\/s26092782","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:01:18Z","timestamp":1777474878000},"page":"2782","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Unsupervised Image Stitching Framework via Joint Iterative Optimization of Deformation Estimation, Feature Registration, and Seamless Blending"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8905-3919","authenticated-orcid":false,"given":"Baian","family":"Ning","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence & Low-Altitude Technology, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence & Low-Altitude Technology, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoxin","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence & Low-Altitude Technology, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Lou","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence & Low-Altitude Technology, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence & Low-Altitude Technology, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4004-9808","authenticated-orcid":false,"given":"Shanggang","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence & Low-Altitude Technology, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s11263-006-0002-3","article-title":"Automatic panoramic image stitching using invariant features","volume":"74","author":"Brown","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/0600000009","article-title":"Image alignment and stitching: A tutorial","volume":"2","author":"Szeliski","year":"2007","journal-title":"Found. Trends Comput. Graph. Vis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/PL00013269","article-title":"Straight lines have to be straight","volume":"13","author":"Devernay","year":"2001","journal-title":"Mach. Vis. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2","DOI":"10.5772\/57160","article-title":"Stitching images with arbitrary lens distortions","volume":"11","author":"Ju","year":"2014","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zaragoza, J., Chin, T.J., Brown, M.S., and Suter, D. (2013). As-projective-as-possible image stitching with moving DLT. 2013 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2013.303"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chang, C.H., Sato, Y., and Chuang, Y.Y. (2014). Shape-preserving half-projective warps for image stitching. 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.422"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lin, C.C., Pankanti, S.U., Natesan Ramamurthy, K., and Aravkin, A.Y. (2015). Adaptive as-natural-as-possible image stitching. 2015 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2015.7298719"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gao, J., Kim, S.J., and Brown, M.S. (2011). Constructing image panoramas using dual-homography warping. CVPR 2011, IEEE.","DOI":"10.1109\/CVPR.2011.5995433"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Lin, K., Jiang, N., Cheong, L.F., Do, M., and Lu, J. (2016). Seagull: Seam-guided local alignment for parallax-tolerant image stitching. European Conference on Computer Vision, Springer International Publishing.","DOI":"10.1007\/978-3-319-46487-9_23"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fitzgibbon, A.W. (2001). Simultaneous linear estimation of multiple view geometry and lens distortion. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, IEEE.","DOI":"10.1109\/CVPR.2001.990465"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Byr\u00f6d, M., Brown, M., and \u00c5str\u00f6m, K. (2009). Minimal solutions for panoramic stitching with radial distortion. The 20th British Machine Vision Conference, British Machine Vision Association (BMVA).","DOI":"10.5244\/C.23.41"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Essien, E., and Frimpong, S. (2025). Enhancing autonomous truck navigation in underground mines: A review of 3D object detection systems, challenges, and future trends. Drones, 9.","DOI":"10.20944\/preprints202505.0678.v1"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, F., and Liu, F. (2014). Parallax-tolerant image stitching. 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.423"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1109\/34.888718","article-title":"A flexible new technique for camera calibration","volume":"22","author":"Zhang","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"327","DOI":"10.5201\/ipol.2014.106","article-title":"Automatic lens distortion correction using one-parameter division models","volume":"4","author":"Alvarez","year":"2014","journal-title":"Image Process. Line"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"180373","DOI":"10.1109\/ACCESS.2019.2959204","article-title":"Robust line-based radial distortion estimation from a single image","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rong, J., Huang, S., Shang, Z., and Ying, X. (2016). Radial lens distortion correction using convolutional neural networks trained with synthesized images. Asian Conference on Computer Vision, Springer International Publishing.","DOI":"10.1007\/978-3-319-54187-7_3"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Han, D., Chen, L., Guo, Z., and Yang, C. (2022). A fisheye distortion correction method based on deep learning. 2022 6th International Conference on Electronic Information Technology and Computer Engineering, IEEE.","DOI":"10.1145\/3573428.3573692"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1109\/34.754589","article-title":"True multi-image alignment and its application to mosaicing and lens distortion correction","volume":"21","author":"Sawhney","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1016\/S0262-8856(02)00064-1","article-title":"Image mosaicing using sequential bundle adjustment","volume":"20","author":"McLauchlan","year":"2002","journal-title":"Image Vis. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6184","DOI":"10.1109\/TIP.2021.3092828","article-title":"Unsupervised deep image stitching: Reconstructing stitched features to images","volume":"30","author":"Nie","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.neucom.2021.03.099","article-title":"Image stitching via deep homography estimation","volume":"450","author":"Zhao","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hittawe, M.M., Sidib\u00e9, D., and M\u00e9riaudeau, F. (2015). A machine vision based approach for timber knots detection. Twelfth International Conference on Quality Control by Artificial Vision 2015, SPIE.","DOI":"10.1117\/12.2182770"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lelowicz, K. (2019). Camera model for lens with strong distortion in automotive application. 2019 24th International Conference on Methods and Models in Automation and Robotics (MMAR), IEEE.","DOI":"10.1109\/MMAR.2019.8864659"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1007\/s11760-019-01466-9","article-title":"Quality evaluation-based iterative seam estimation for image stitching","volume":"13","author":"Liao","year":"2019","journal-title":"Signal Image Video Process."},{"key":"ref_26","unstructured":"Song, W., Li, P., and Wang, M. (2024). Transmission line detection based on improved hough transform. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1109\/RBME.2018.2798701","article-title":"A survey of graph cuts\/graph search based medical image segmentation","volume":"11","author":"Chen","year":"2018","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10589-024-00589-1","article-title":"The Levenberg\u2013Marquardt method: An overview of modern convergence theories and more","volume":"89","author":"Fischer","year":"2024","journal-title":"Comput. Optim. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1002\/wics.1202","article-title":"Gauss\u2013newton method","volume":"4","author":"Wang","year":"2012","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Beya, O., Hittawe, M.M., Alashkar, T., Fauvet, E., and Laligant, O. (2015). Applying non linear approach for ecg denoising and waves localization. 2015 11th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), IEEE.","DOI":"10.1109\/SITIS.2015.110"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Feng, C.B., Zhang, J., Li, J., and Zhou, Y. (2024). Seam mask guided partial reconstruction with quantum-inspired local aggregation for deep image stitching. ICASSP 2024\u20142024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP48485.2024.10447800"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Liu, J., Liang, A., Zhao, E., Pang, M., and Zhang, D. (2023). Homography matrix-based local motion consistent matching for remote sensing images. Remote Sens., 15.","DOI":"10.3390\/rs15133379"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hore, A., and Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. 2010 20th International Conference on Pattern Recognition, IEEE.","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Falkenhagen, U., K\u00f6ssler, W., and Lenz, H.J. (2019). A likelihood ratio test for inlier detection. Workshop on Stochastic Models, Statistics and Their Application, Springer International Publishing.","DOI":"10.1007\/978-3-030-28665-1_26"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/9\/2782\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T04:16:35Z","timestamp":1778386595000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/9\/2782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":34,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["s26092782"],"URL":"https:\/\/doi.org\/10.3390\/s26092782","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]}}}