ICCV 2021 OCR领域相关14篇论文回顾
共 3293字，需浏览 7分钟
· 2021-11-11
点击下方“AI算法与图像处理”，一起进步！
重磅干货，第一时间送达
ICCV 2021已于10月17日结束，论文可以在官网全文浏览及下载（网址：https://openaccess.thecvf.com/ICCV2021?day=all），据初步统计，ICCV 2021共收录与文档图像分析与识别相关的论文约14篇，覆盖文档图像处理（矫正、去噪）、文字检测及识别、文档图像理解及预训练模型、文档图像编辑、表格结构识别、文档图像合成（字体、手写、文档生成）等多个方向。具体情况如下：
文字图像处理（文档图像矫正、去噪）：2篇
Sagnik Das; Kunwar Yashraj Singh; Jon Wu; Erhan Bas; Vijay Mahadevan; Rahul Bhotika; Dimitris Samaras, End-to-End Piece-Wise Unwarping of Document Images, ICCV 2021.
- Project page: https://sagniklp.github.io/PiecewiseUnwarp/
Mehrdad J. Gangeh; Marcin Plata; Hamid R. Motahari Nezhad; Nigel P Duffy，End-to-End Unsupervised Document Image Blind Denoising, ICCV 2021.
场景文字检测：1篇
Shi-Xue Zhang; Xiaobin Zhu; Chun Yang; Hongfa Wang; Xu-Cheng Yin, Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection, ICCV 2021.
- Code：https://github.com/GXYM/TextBPN
场景文字识别：2篇
Ayan Kumar Bhunia; Aneeshan Sain; Amandeep Kumar; Shuvozit Ghose; Pinaki Nath Chowdhury; Yi-Zhe Song, Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition, ICCV 2021. Yuxin Wang; Hongtao Xie; Shancheng Fang; Jing Wang; Shenggao Zhu; Yongdong Zhang， From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network, ICCV 2021. - Code：https://github.com/wangyuxin87/VisionLAN
跨域文字识别：2篇
Ayan Kumar Bhunia; Aneeshan Sain; Pinaki Nath Chowdhury; Yi-Zhe Song, Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation, ICCV 2021. Ayan Kumar Bhunia; Pinaki Nath Chowdhury; Aneeshan Sain; Yi-Zhe Song, Towards the Unseen: Iterative Text Recognition by Distilling from Errors, ICCV 2021.
文字编辑：2篇
Vijay Kumar B G; Jeyasri Subramanian; Varnith Chordia; Eugene Bart; Shaobo Fang; Kelly Guan; Raja Bala, STRIVE: Scene Text Replacement In Videos, ICCV 2021. - Dataset: https://striveiccv2021.github.io/STRIVE-ICCV2021/ Wataru Shimoda; Daichi Haraguchi; Seiichi Uchida; Kota Yamaguchi, De-Rendering Stylized Texts, ICCV 2021.
表格结构识别：1篇
Wenyuan Xue; Baosheng Yu; Wen Wang; Dacheng Tao; Qingyong Li, TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition, ICCV 2021.
文档理解与预训练模型：1篇
Srikar Appalaraju; Bhavan Jasani; Bhargava Urala Kota; Yusheng Xie; R. Manmatha, DocFormer: End-to-End Transformer for Document Understanding, ICCV 2021.
文档图像合成：3篇 (字体生成、文档生成、手写文字合成）
Song Park; Sanghyuk Chun; Junbum Cha; Bado Lee; Hyunjung Shim, Multiple Heads Are Better Than One: Few-Shot Font Generation With Multiple Localized Experts, ICCV 2021. - Code: https://github.com/clovaai/mxfont Kota Yamaguchi, CanvasVAE: Learning To Generate Vector Graphic Documents, ICCV 2021.
Ankan Kumar Bhunia; Salman Khan; Hisham Cholakkal; Rao Muhammad Anwer; Fahad Shahbaz Khan; Mubarak Shah，Handwriting Transformers, ICCV 2021. - Code: https://github.com/ankanbhunia/Handwriting-Transformers
交流群
欢迎加入公众号读者群一起和同行交流，目前有美颜、三维视觉、计算摄影、检测、分割、识别、医学影像、GAN、算法竞赛等微信群
个人微信（如果没有备注不拉群！） 请注明：地区+学校/企业+研究方向+昵称
下载1：何恺明顶会分享
在「AI算法与图像处理」公众号后台回复：何恺明，即可下载。总共有6份PDF，涉及 ResNet、Mask RCNN等经典工作的总结分析
下载2：终身受益的编程指南：Google编程风格指南
在「AI算法与图像处理」公众号后台回复：c++，即可下载。历经十年考验，最权威的编程规范！
下载3 CVPR2021 在「AI算法与图像处理」公众号后台回复：CVPR，即可下载1467篇CVPR 2020论文 和 CVPR 2021 最新论文
