Learning Enriched Features for Real Image Restoration and Enhancement

计算机科学 卷积神经网络 水准点(测量) 人工智能 块(置换群论) 图像分辨率 卷积(计算机科学) 图像(数学) 特征(语言学) 模式识别(心理学) 计算机视觉 人工神经网络 几何学 哲学 语言学 数学 地理 大地测量学
作者
Syed Waqas Zamir,Aditya Arora,Salman Khan,Munawar Hayat,Fahad Shahbaz Khan,Ming–Hsuan Yang,Ling Shao
出处
期刊:Lecture Notes in Computer Science 卷期号:: 492-511 被引量:234
标识
DOI:10.1007/978-3-030-58595-2_30
摘要

With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography and medical imaging. Recently, convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. Existing CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatially precise but contextually less robust results are achieved, while in the latter case, semantically reliable but spatially less accurate outputs are generated. In this paper, we present an architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network and receiving strong contextual information from the low-resolution representations. The core of our approach is a multi-scale residual block containing several key elements: (a) parallel multi-resolution convolution streams for extracting multi-scale features, (b) information exchange across the multi-resolution streams, (c) spatial and channel attention mechanisms for capturing contextual information, and (d) attention based multi-scale feature aggregation. In a nutshell, our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Extensive experiments on five real image benchmark datasets demonstrate that our method, named as MIRNet, achieves state-of-the-art results for image denoising, super-resolution, and image enhancement. The source code and pre-trained models are available at https://github.com/swz30/MIRNet .
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
刚刚
刚刚
1秒前
fairy发布了新的文献求助10
1秒前
sci来来来完成签到,获得积分10
1秒前
西门子云发布了新的文献求助10
1秒前
1秒前
淡淡代玉发布了新的文献求助10
2秒前
pipi完成签到,获得积分10
2秒前
YW发布了新的文献求助10
2秒前
汉堡包应助丁丽采纳,获得10
2秒前
无花果应助四叶草采纳,获得10
2秒前
SciGPT应助111采纳,获得10
4秒前
梨核完成签到 ,获得积分20
4秒前
安静一曲发布了新的文献求助10
4秒前
快乐梦松完成签到,获得积分20
4秒前
量子星尘发布了新的文献求助10
4秒前
leena发布了新的文献求助10
4秒前
oddity完成签到 ,获得积分10
4秒前
ljydhr发布了新的文献求助10
5秒前
Helen完成签到,获得积分10
5秒前
yyhgyg发布了新的文献求助10
7秒前
敏感草丛发布了新的文献求助10
7秒前
7秒前
蜗牛完成签到,获得积分10
7秒前
阿来哈哈发布了新的文献求助10
8秒前
george发布了新的文献求助10
9秒前
9秒前
Hello应助ysy采纳,获得10
9秒前
杀死比尔发布了新的文献求助10
10秒前
eloise完成签到,获得积分10
10秒前
liyuxuan完成签到,获得积分10
10秒前
10秒前
无花果应助001采纳,获得10
10秒前
社科狗发布了新的文献求助10
11秒前
ZWZ发布了新的文献求助160
11秒前
香蕉妙菱发布了新的文献求助10
12秒前
12秒前
知性的冰棍完成签到,获得积分10
12秒前
Andy1201应助摆烂好爽采纳,获得20
13秒前
高分求助中
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
Effective Learning and Mental Wellbeing 300
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 3974463
求助须知:如何正确求助?哪些是违规求助? 3518823
关于积分的说明 11196212
捐赠科研通 3255008
什么是DOI,文献DOI怎么找? 1797655
邀请新用户注册赠送积分活动 877052
科研通“疑难数据库(出版商)”最低求助积分说明 806130