{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:57:01Z","timestamp":1743116221098,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620531"},{"type":"electronic","value":"9789819620548"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2054-8_23","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:47:58Z","timestamp":1735832878000},"page":"304-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DocMamba: Robust Document Image Dewarping via\u00a0Selective State Space Sequence Modeling"],"prefix":"10.1007","author":[{"given":"Miaolin","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Brown, M., Seales, W.: Document restoration using 3D shape: a general deskewing algorithm for arbitrarily warped documents. In: Proceedings Eighth IEEE International Conference on Computer Vision, vol. 2, pp. 367\u2013374 (2001)","DOI":"10.1109\/ICCV.2001.937649"},{"issue":"10","key":"23_CR2","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1109\/TPAMI.2004.87","volume":"26","author":"M Brown","year":"2004","unstructured":"Brown, M., Seales, W.: Image restoration of arbitrarily warped documents. IEEE Trans. Pattern Anal. Mach. Intell. 26(10), 1295\u20131306 (2004)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Cao, H., Ding, X., Liu, C.: Rectifying the bound document image captured by the camera: a model based approach. In: Seventh International Conference on Document Analysis and Recognition, Proceedings, vol. 1, pp. 71\u201375 (2003)","DOI":"10.1109\/ICDAR.2003.1227630"},{"key":"23_CR4","unstructured":"Dao, T., Gu, A.: Transformers are SSMS: generalized models and efficient algorithms through structured state space duality. arXiv abs\/2405.21060 (2024)"},{"key":"23_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: IEEE\/CVF International Conference on Computer Vision, pp. 131\u2013140 (2019)","DOI":"10.1109\/ICCV.2019.00022"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Das, S., et al.: End-to-end piece-wise unwarping of document images. In: IEEE\/CVF International Conference on Computer Vision, pp. 4248\u20134257 (2021)","DOI":"10.1109\/ICCV48922.2021.00423"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Feng, H., Liu, S., Deng, J., Zhou, W., Li, H.: Deep unrestricted document image rectification. IEEE Trans. Multimedia 26, 6142\u20136154 (2023)","DOI":"10.1109\/TMM.2023.3347094"},{"key":"23_CR8","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 29th ACM International Conference on Multimedia, pp. 273\u2013281 (2021)","DOI":"10.1145\/3474085.3475388"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Feng, H., Zhou, W., Deng, J., Wang, Y., Li, H.: Geometric representation learning for document image rectification. In: European Conference on Computer Vision, pp. 475\u2013492 (2022)","DOI":"10.1007\/978-3-031-19836-6_27"},{"key":"23_CR10","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv abs\/2312.00752 (2023)"},{"key":"23_CR11","unstructured":"Gu, A., Goel, K., R\u2019e, C.: Efficiently modeling long sequences with structured state spaces. arXiv abs\/2111.00396 (2021)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Pan, P., Xie, S., Sun, J., Naoi, S.: A book dewarping system by boundary-based 3D surface reconstruction. In: International Conference on Document Analysis and Recognition, pp. 403\u2013407 (2013)","DOI":"10.1109\/ICDAR.2013.88"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, X., Long, R., Xue, N., Yang, Z., Yao, C., Xia, G.S.: Revisiting document image dewarping by grid regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4543\u20134552 (2022)","DOI":"10.1109\/CVPR52688.2022.00450"},{"key":"23_CR14","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: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00494"},{"issue":"7","key":"23_CR15","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1109\/TIP.2009.2019301","volume":"18","author":"HI Koo","year":"2009","unstructured":"Koo, H.I., Kim, J., Cho, N.I.: Composition of a dewarped and enhanced document image from two view images. IEEE Trans. Image Process. 18(7), 1551\u20131562 (2009)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Lavialle, O., Molines, X., Angella, F., Baylou, P.: Active contours network to straighten distorted text lines. In: International Conference on Image Processing, vol. 3, pp. 748\u2013751 (2001)","DOI":"10.1109\/ICIP.2001.958227"},{"key":"23_CR17","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1965","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. Soviet Phys. Doklady 10, 707\u2013710 (1965)","journal-title":"Soviet Phys. Doklady"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, X., Chen, Q., Xiang, Q.: Foreground and text-lines aware document image rectification. In: IEEE\/CVF International Conference on Computer Vision, pp. 19517\u201319526 (2023)","DOI":"10.1109\/ICCV51070.2023.01793"},{"key":"23_CR19","first-page":"1","volume":"38","author":"X Li","year":"2019","unstructured":"Li, X., Zhang, B., Liao, J., Sander, P.: Document rectification and illumination correction using a patch-based CNN. ACM Trans. Graph. 38, 1\u201311 (2019)","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"23_CR20","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TPAMI.2007.70724","volume":"30","author":"J Liang","year":"2008","unstructured":"Liang, J., DeMenthon, D., Doermann, D.: Geometric rectification of camera-captured document images. IEEE Trans. Pattern Anal. Mach. Intell. 30(4), 591\u2013605 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107576","volume":"108","author":"X Liu","year":"2020","unstructured":"Liu, X., Meng, G., Fan, B., Xiang, S., Pan, C.: Geometric rectification of document images using adversarial gated unwarping network. Pattern Recogn. 108, 107576 (2020)","journal-title":"Pattern Recogn."},{"key":"23_CR22","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 SIGGRAPH 2022 Conference Proceedings (2022)","DOI":"10.1145\/3528233.3530756"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Meng, G., Wang, Y., Qu, S., Xiang, S., Pan, C.: Active flattening of curved document images via two structured beams. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3890\u20133897 (2014)","DOI":"10.1109\/CVPR.2014.497"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Morris, A.C., Maier, V., Green, P.D.: From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition. In: Interspeech (2004)","DOI":"10.21437\/Interspeech.2004-668"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition, vol.\u00a02, pp. 629\u2013633 (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"issue":"2","key":"23_CR26","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1109\/TPAMI.2006.40","volume":"28","author":"CL Tan","year":"2006","unstructured":"Tan, C.L., Zhang, L., Zhang, Z., Xia, T.: Restoring warped document images through 3D shape modeling. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 195\u2013208 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Verhoeven, F., Magne, T., Sorkine-Hornung, O.: Uvdoc: neural grid-based document unwarping. In: SIGGRAPH Asia (2023)","DOI":"10.1145\/3610548.3618174"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Wada, T., Ukida, H., Matsuyama, T.: Shape from shading with interreflections under proximal light source-3D shape reconstruction of unfolded book surface from a scanner image. In: Proceedings of IEEE International Conference on Computer Vision, pp. 66\u201371 (1995)","DOI":"10.1109\/ICCV.1995.466805"},{"key":"23_CR29","unstructured":"Wang, Z., Simoncelli, E., Bovik, A.: Multiscale structural similarity for image quality assessment. In: The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers, vol.\u00a02, pp. 1398\u20131402 (2003)"},{"issue":"4","key":"23_CR30","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Xie, G.W., Yin, F., Zhang, X.Y., Liu, C.L.: Dewarping document image by displacement flow estimation with fully convolutional network. arXiv abs\/2104.06815 (2020)","DOI":"10.1007\/978-3-030-57058-3_10"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Xie, G.W., Yin, F., Zhang, X.Y., Liu, C.L.: Document dewarping with control points. In: IEEE International Conference on Document Analysis and Recognition (2022)","DOI":"10.1007\/978-3-030-86549-8_30"},{"issue":"2","key":"23_CR33","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1109\/TPAMI.2017.2675980","volume":"40","author":"S You","year":"2018","unstructured":"You, S., Matsushita, Y., Sinha, S., Bou, Y., Ikeuchi, K.: Multiview rectification of folded documents. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 505\u2013511 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR34","unstructured":"Zhang, J., Chen, B., Cheng, H., Guo, F., Ding, K., Jin, L.: Docaligner: annotating real-world photographic document images by simply taking pictures. arXiv preprint arXiv:2306.05749 (2023)"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, J., Peng, D., Liu, C., Zhang, P., Jin, L.: Docres: a generalist model toward unifying document image restoration tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15654\u201315664 (2024)","DOI":"10.1109\/CVPR52733.2024.01482"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:43:03Z","timestamp":1742694183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}