{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/doctr-document-image-transformer-for","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","arxiv_id":"2110.12942","date":"2021-10-25","proceeding":null,"authors":["Hao Feng","Yuechen Wang","Wengang Zhou","Jiajun Deng","Houqiang Li"],"abstract":"In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifically, DocTr consists of a geometric unwarping transformer and an illumination correction transformer. By setting a set of learned query embedding, the geometric unwarping transformer captures the global context of the document image by self-attention mechanism and decodes the pixel-wise displacement solution to correct the geometric distortion. After geometric unwarping, our illumination correction transformer further removes the shading artifacts to improve the visual quality and OCR accuracy. Extensive evaluations are conducted on several datasets, and superior results are reported against the state-of-the-art methods. Remarkably, our DocTr achieves 20.02% Character Error Rate (CER), a 15% absolute improvement over the state-of-the-art methods. Moreover, it also shows high efficiency on running time and parameter count. The results will be available at https://github.com/fh2019ustc/DocTr for further comparison.","url_abs":"https://arxiv.org/abs/2110.12942v2","url_pdf":"https://arxiv.org/pdf/2110.12942v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"doctr-document-image-transformer-for","repo_url":"https://github.com/fh2019ustc/doctr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"doctr-document-image-transformer-for","repo_url":"https://github.com/xiaomore/document-image-dewarping","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.12942","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}