Local Texture Pattern Estimation for Image Detail Super-Resolution

人工智能 计算机视觉 图像纹理 计算机科学 纹理(宇宙学) 模式识别(心理学) 图像分割 图像分辨率 图像(数学) 图像处理
作者
Fan Fan,Yang Zhao,Yuan Chen,Nannan Li,Wei Jia,Ronggang Wang
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:47 (6): 4517-4534 被引量:9
标识
DOI:10.1109/tpami.2025.3545571
摘要

In the image super-resolution (SR) field, recovering missing high-frequency textures has always been an important goal. However, deep SR networks based on pixel-level constraints tend to focus on stable edge details and cannot effectively restore random high-frequency textures. It was not until the emergence of the generative adversarial network (GAN) that GAN-based SR models achieved realistic texture restoration and quickly became the mainstream method for texture SR. However, GAN-based SR models still have some drawbacks, such as relying on a large number of parameters and generating fake textures that are inconsistent with ground truth. Inspired by traditional texture analysis research, this paper proposes a novel SR network based on local texture pattern estimation (LTPE), which can restore fine high-frequency texture details without GAN. A differentiable local texture operator is first designed to extract local texture structures, and a texture enhancement branch is used to predict the high-resolution local texture distribution based on the LTPE. Then, the predicted high-resolution texture structure map can be used as a reference for the texture fusion SR branch to obtain high-quality texture reconstruction. Finally, $L_{1}$L1 loss and Gram loss are simultaneously used to optimize the network. Experimental results demonstrate that the proposed method can effectively recover high-frequency texture without using GAN structures. In addition, the restored high-frequency details are constrained by local texture distribution, thereby reducing significant errors in texture generation.
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
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
yrz完成签到,获得积分20
1秒前
斯文败类的应助被xwx采纳,获得10
2秒前
徐丹枫发布了新的文献求助10
2秒前
2秒前
乌龙茶发布了新的文献求助10
2秒前
我是老大的应助被科研通管家采纳,获得10
2秒前
深情安青的应助被科研通管家采纳,获得10
3秒前
3秒前
FashionBoy的应助被科研通管家采纳,获得50
3秒前
情怀的应助被科研通管家采纳,获得10
3秒前
Hase的应助被科研通管家采纳,获得30
3秒前
秋风的应助被科研通管家采纳,获得10
3秒前
华仔的应助被科研通管家采纳,获得10
3秒前
酷波er的应助被科研通管家采纳,获得10
3秒前
CipherSage的应助被科研通管家采纳,获得20
4秒前
勤奋一一的应助被科研通管家采纳,获得10
4秒前
研友_VZG7GZ的应助被科研通管家采纳,获得10
4秒前
4秒前
王英霖的应助被科研通管家采纳,获得20
4秒前
秋风的应助被科研通管家采纳,获得20
4秒前
syvshc的应助被科研通管家采纳,获得10
4秒前
李爱国的应助被科研通管家采纳,获得10
4秒前
科研通AI2S的应助被科研通管家采纳,获得10
5秒前
Luna666完成签到,获得积分10
5秒前
乐乐的应助被科研通管家采纳,获得10
5秒前
5秒前
wanci的应助被科研通管家采纳,获得50
5秒前
5秒前
丁亦竹发布了新的文献求助100
6秒前
能干灯泡发布了新的文献求助10
7秒前
赘婿的应助被观山青采纳,获得10
7秒前
传奇3的应助被平常的路人采纳,获得10
7秒前
我家电脑完成签到 ,获得积分10
8秒前
9秒前
科目三的应助被XPR采纳,获得10
9秒前
eeeee完成签到,获得积分10
10秒前
木子发布了新的文献求助10
11秒前
13秒前
memebao完成签到,获得积分10
14秒前
瑶瑶完成签到,获得积分10
15秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181767
求助须知:如何正确求助?哪些是违规求助? 9571480
关于积分的说明 21818225
捐赠科研通 7778030
什么是DOI,文献DOI怎么找? 3433524
关于科研通互助平台的介绍 2557696
邀请新用户注册赠送积分活动 2479598