Rethinking Supervision in Document Unwarping: A Self-consistent Flow-free Approach

计算机科学 整改 图像扭曲 杠杆(统计) 人工智能 数字化 失真(音乐) 情报检索 深度学习 计算机视觉 数据挖掘 放大器 计算机网络 功率(物理) 物理 带宽(计算) 量子力学
作者
Shaokai Liu,Hao Feng,Wengang Zhou
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tcsvt.2023.3336068
摘要

In recent years, the proliferation of smartphones has led to an upsurge in the digitization of document files via these portable devices. However, images captured by smartphones often suffer from distortions, thereby negatively affecting digital preservation and downstream applications. To address this issue, we introduce DRNet, a novel deep network for document image rectification. Our approach is based on three key designs. Firstly, we exploit the intrinsic geometric consistency inherent in document images to guide the learning process of distortion rectification. Secondly, we design a coarse-to-fine rectification network to leverage the representations derived from the distorted document image, thereby enhancing the rectification result. Thirdly, we propose a unique perspective for supervising the learning of rectification networks, where undistorted document images are employed for supervision, which is free of warping mesh as ground truth in existing methods. Technically, both low-level pixel alignment and high-level semantic alignment jointly contribute to the learning of the mapping relationship between deformed document images and distortion-free ones. We evaluate our method on the challenging DocUNet Benchmark dataset, where it sets a series of state-of-the-art records, demonstrating the superiority of our approach compared to existing learning-based solutions. Additionally, we conduct a comprehensive series of ablation experiments to further validate the effectiveness and merits of our method.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刘YF发布了新的文献求助10
3秒前
3秒前
orixero应助ty采纳,获得10
5秒前
6秒前
拉长的冷霜完成签到,获得积分10
6秒前
8秒前
英姑应助ccmaxp采纳,获得10
8秒前
wu先生完成签到,获得积分10
11秒前
jmn发布了新的文献求助10
11秒前
11秒前
15秒前
15秒前
16秒前
大米完成签到,获得积分10
16秒前
17秒前
17秒前
ty发布了新的文献求助10
19秒前
田様应助不安的小刺猬采纳,获得10
21秒前
damian完成签到,获得积分10
21秒前
JamesPei应助Fengh采纳,获得10
21秒前
WD发布了新的文献求助10
21秒前
善良天抒发布了新的文献求助10
22秒前
量子星尘发布了新的文献求助30
23秒前
23秒前
xiaojinyu发布了新的文献求助10
24秒前
zxh完成签到,获得积分10
24秒前
26秒前
天天快乐应助obsidian_virgo采纳,获得10
26秒前
27秒前
27秒前
大白完成签到,获得积分10
27秒前
Qiancheng完成签到,获得积分10
27秒前
Owen应助刘YF采纳,获得10
28秒前
ccmaxp发布了新的文献求助10
29秒前
29秒前
ZhaoPeng发布了新的文献求助10
30秒前
一袋薯片发布了新的文献求助10
30秒前
30秒前
gcl应助zwk采纳,获得30
30秒前
31秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975543
求助须知:如何正确求助?哪些是违规求助? 3519971
关于积分的说明 11200248
捐赠科研通 3256311
什么是DOI,文献DOI怎么找? 1798213
邀请新用户注册赠送积分活动 877446
科研通“疑难数据库(出版商)”最低求助积分说明 806338