{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:52:43Z","timestamp":1769831563347,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705458","type":"print"},{"value":"9783031705465","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70546-5_20","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:02:47Z","timestamp":1725944567000},"page":"343-358","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Coarse-to-Fine Document Image Registration for\u00a0Dewarping"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8783-0326","authenticated-orcid":false,"given":"Weiguang","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0918-4606","authenticated-orcid":false,"given":"Qiufeng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3034-9639","authenticated-orcid":false,"given":"Kaizhu","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Xiaomeng","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Fengjun","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"20_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/978-3-030-86549-8_30","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"G-W Xie","year":"2021","unstructured":"Xie, G.-W., Yin, F., Zhang, X.-Y., Liu, C.-L.: Document dewarping with control points. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 466\u2013480. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_30"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Ma, K., Shu, Z., Bai, X., Wang, J., Samaras, D.: DocUNet: document image unwarping via a stacked U-Net. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700\u20134709 (2018)","DOI":"10.1109\/CVPR.2018.00494"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Xie, G., Yin, F., Zhang, X., Liu, C.: Dewarping document image by displacement flow estimation with fully convolutional network. In: International Workshop on Document Analysis Systems (DAS), pp. 131\u2013144 (2020)","DOI":"10.1007\/978-3-030-57058-3_10"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1007\/978-3-030-63833-7_13","volume-title":"Neural Information Processing","author":"J Li","year":"2020","unstructured":"Li, J., Wang, Q.-F., Zhang, R., Huang, K.: Adversarial rectification network for\u00a0scene text regularization. In: Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H., King, I. (eds.) ICONIP 2020. LNCS, vol. 12533, pp. 152\u2013163. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-63833-7_13"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Das, S., Ma, K., Shu, Z., Samaras, D., Shilkrot, R.: DewarpNet: single-image document unwarping with stacked 3D and 2D regression networks. In: International Conference on Computer Vision (ICCV), pp. 131\u2013140 (2019)","DOI":"10.1109\/ICCV.2019.00022"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Li, P., Quan, W., Guo, J., Yan, D.-M.: Layout-aware single-image document flattening. ACM Trans. Graph. (TOG) 43(1) (2023)","DOI":"10.1145\/3627818"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Ma, K., Das, S., Shu, Z., Samaras, D.: Learning from documents in the wild to improve document unwarping. In: ACM Special Interest Group on Computer Graphics (SIGGRAPH), Conference Proceedings, pp. 1\u20139 (2022)","DOI":"10.1145\/3528233.3530756"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Verhoeven, F., Magne, T., Sorkine-Hornung, O.: UVDoc: neural grid-based document unwarping. In: ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH ASIA) (2023)","DOI":"10.1145\/3610548.3618174"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Xue, C., Tian, Z., Zhan, F., Lu, S., Bai, S.: Fourier document restoration for robust document dewarping and recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4573\u20134582 (2022)","DOI":"10.1109\/CVPR52688.2022.00453"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Zhu, S., Liu, X.: PMatch: paired masked image modeling for dense geometric matching, March 2023. arXiv:2303.17342 [cs]","DOI":"10.1109\/CVPR52729.2023.02098"},{"key":"20_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102036","volume":"71","author":"B Kim","year":"2021","unstructured":"Kim, B., Kim, D.H., Park, S.H., Kim, J., Lee, J.-G., Ye, J.C.: CycleMorph: cycle consistent unsupervised deformable image registration. Med. Image Anal. 71, 102036 (2021)","journal-title":"Med. Image Anal."},{"issue":"8","key":"20_CR12","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TMI.2019.2897538","volume":"38","author":"G Balakrishnan","year":"2019","unstructured":"Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38(8), 1788\u20131800 (2019)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"20_CR13","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s11263-020-01359-2","volume":"129","author":"J Ma","year":"2021","unstructured":"Ma, J., Jiang, X., Fan, A., Jiang, J., Yan, J.: Image matching from handcrafted to deep features: a survey. Int. J. Comput. Vis. 129, 23\u201379 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"20_CR14","unstructured":"Zheng, D., Wu, X.-M., Liu, Z., Meng, J., Zheng, W.-S.: DiffuVolume: diffusion model for volume based stereo matching, August 2023. arXiv:2308.15989 [cs]"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Chang, J., Yu, J., Zhang, T.: Structured epipolar matcher for local feature matching, April 2023. arXiv:2303.16646 [cs]. http:\/\/arxiv.org\/abs\/2303.16646","DOI":"10.1109\/CVPRW59228.2023.00657"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Melekhov, I., Tiulpin, A., Sattler, T., Pollefeys, M., Rahtu, E., Kannala, J.: DGC-Net: dense geometric correspondence network, October 2018. arXiv:1810.08393 [cs]","DOI":"10.1109\/WACV.2019.00115"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Jeong, J., Cai, H., Garrepalli, R., Porikli, F.: DistractFlow: improving optical flow estimation via realistic distractions and pseudo-labeling, March 2023. arXiv:2303.14078 [cs]","DOI":"10.1109\/CVPR52729.2023.01316"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: AccFlow: backward accumulation for long-range optical flow, August 2023. arXiv:2308.13133 [cs]","DOI":"10.1109\/ICCV51070.2023.01113"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, J., Cho, M.: TransforMatcher: match-to-match attention for semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138707 (2022)","DOI":"10.1109\/CVPR52688.2022.00850"},{"key":"20_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102615","volume":"82","author":"J Chen","year":"2022","unstructured":"Chen, J., Frey, E.C., He, Y., Segars, W.P., Li, Y., Du, Y.: TransMorph: transformer for unsupervised medical image registration. Med. Image Anal. 82, 102615 (2022)","journal-title":"Med. Image Anal."},{"key":"20_CR21","unstructured":"Zhang, J., Chen, B., Cheng, H., Guo, F., Ding, K., Jin, L.: DocAligner: annotating real-world photographic document images by simply taking pictures, June 2023. arXiv:2306.05749 [cs]"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Burie, J.-C., et al.: ICDAR2015 competition on smartphone document capture and OCR (SmartDoc). In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1161\u20131165. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333943"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, B., Liao, J., Sander, P.V.: Document rectification and illumination correction using a patch-based CNN. ACM Trans. Graph. (TOG) 38(6), 1\u201311 (2019)","DOI":"10.1145\/3355089.3356563"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Hertlein, F., Naumann, A., Philipp, P.: Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping. Int. J. Doc. Anal. Recogn. (IJDAR), 1\u201312 (2023)","DOI":"10.1007\/s10032-023-00434-x"},{"key":"20_CR25","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems (NIPS), vol.\u00a030 (2017)"},{"key":"20_CR26","unstructured":"Chen, Y., Mancini, M., Zhu, X., Akata, Z.: Semi-supervised and unsupervised deep visual learning: a survey, August 2022. arXiv:2208.11296 [cs]"},{"issue":"14","key":"20_CR27","doi-asserted-by":"publisher","first-page":"e49","DOI":"10.1093\/bioinformatics\/btl242","volume":"22","author":"KM Borgwardt","year":"2006","unstructured":"Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H.-P., Sch\u00f6lkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14), e49\u2013e57 (2006)","journal-title":"Bioinformatics"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Feng, H., Wang, Y., Zhou, W., Deng, J., Li, H.: DocTr: document image transformer for geometric unwarping and illumination correction. In: Proceedings of the ACM International Conference on Multimedia (MM), pp. 273\u2013281 (2021)","DOI":"10.1145\/3474085.3475388"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Gardner, M.-A., et al.: Learning to predict indoor illumination from a single image. ACM Trans. Graph. (TOG) 36(6), 1\u201314 (2017)","DOI":"10.1145\/3130800.3130891"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, X., Pun, C.-M., Cun, X.: High-resolution document shadow removal via a large-scale real-world dataset and a frequency-aware shadow erasing net, September 2023. arXiv:2308.14221 [cs]","DOI":"10.1109\/ICCV51070.2023.01144"},{"issue":"9","key":"20_CR32","first-page":"1183","volume":"46","author":"J Smith","year":"1980","unstructured":"Smith, J., et al.: The Lambertian assumption and Landsat data. Photogramm. Eng. Remote. Sens. 46(9), 1183\u20131189 (1980)","journal-title":"Photogramm. Eng. Remote. Sens."},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"You, S., Matsushita, Y., Sinha, S., Bou, Y., Ikeuchi, K.: Multiview rectification of folded documents. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40(2), 505\u2013511 (2017)","DOI":"10.1109\/TPAMI.2017.2675980"},{"key":"20_CR34","unstructured":"Wang, Z., Simoncelli, E., Bovik, A.: Multiscale structural similarity for image quality assessment. In: Asilomar Conference on Signals, Systems and Computers (CSSC), pp. 1398\u20131402 (2003)"},{"issue":"8","key":"20_CR35","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I., et al.: Binary codes capable of correcting deletions, insertions, and reversals. Soviet Phys. Dokl. 10(8), 707\u2013710 (1966)","journal-title":"Soviet Phys. Dokl."},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Athanasiadis, I., Wadenb\u00e4ck, M., Felsberg, M.: DKM: dense kernelized feature matching for geometry estimation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17\u00a0765\u201317\u00a0775 (2023)","DOI":"10.1109\/CVPR52729.2023.01704"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70546-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T23:06:03Z","timestamp":1732748763000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70546-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705458","9783031705465"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70546-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}