TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment

计算机科学 人工智能 语义学(计算机科学) 光学(聚焦) 卷积神经网络 图像质量 模式识别(心理学) 机器学习 计算机视觉 图像(数学) 程序设计语言 物理 光学
作者
Chaofeng Chen,Jiadi Mo,Jingwen Hou,Haoning Wu,Liang Liao,Wenxiu Sun,Qiong Yan,Weisi Lin
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:33: 2404-2418 被引量:26
标识
DOI:10.1109/tip.2024.3378466
摘要

Image Quality Assessment (IQA) is a fundamental task in computer vision that has witnessed remarkable progress with deep neural networks. Inspired by the characteristics of the human visual system, existing methods typically use a combination of global and local representations (i.e., multi-scale features) to achieve superior performance. However, most of them adopt simple linear fusion of multi-scale features, and neglect their possibly complex relationship and interaction. In contrast, humans typically first form a global impression to locate important regions and then focus on local details in those regions. We therefore propose a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as TOPIQ. Our approach to IQA involves the design of a heuristic coarse-to-fine network (CFANet) that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner. A key component of our approach is the proposed cross-scale attention mechanism, which calculates attention maps for lower level features guided by higher level features. This mechanism emphasizes active semantic regions for low-level distortions, thereby improving performance. TOPIQ can be used for both Full-Reference (FR) and No-Reference (NR) IQA. We use ResNet50 as its backbone and demonstrate that TOPIQ achieves better or competitive performance on most public FR and NR benchmarks compared with state-of-the-art methods based on vision transformers, while being much more efficient (with only ~13% FLOPS of the current best FR method). Codes are released at https://github.com/chaofengc/IQA-PyTorch.
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
Candy发布了新的文献求助10
刚刚
Rondab应助xiaosu采纳,获得10
1秒前
CodeCraft应助LJJ采纳,获得10
2秒前
2秒前
SYLH应助科研通管家采纳,获得20
3秒前
所所应助科研通管家采纳,获得10
3秒前
科研通AI5应助科研通管家采纳,获得10
3秒前
张金蝶完成签到,获得积分10
3秒前
搜集达人应助科研通管家采纳,获得10
4秒前
CAOHOU应助科研通管家采纳,获得10
4秒前
丘比特应助科研通管家采纳,获得10
4秒前
CAOHOU应助科研通管家采纳,获得10
4秒前
赘婿应助科研通管家采纳,获得10
4秒前
量子星尘发布了新的文献求助30
4秒前
SYLH应助科研通管家采纳,获得20
4秒前
4秒前
4秒前
4秒前
CAOHOU应助科研通管家采纳,获得10
4秒前
Lyuhng+1完成签到 ,获得积分10
5秒前
大个应助十九岁的时差采纳,获得10
6秒前
9秒前
桃花落完成签到,获得积分10
12秒前
su发布了新的文献求助10
12秒前
思源应助汪汪采纳,获得10
12秒前
高兴的天蓝完成签到 ,获得积分10
13秒前
13秒前
14秒前
星星应助momo采纳,获得10
14秒前
15秒前
阿钉发布了新的文献求助10
16秒前
科研通AI2S应助愉快的宛儿采纳,获得10
16秒前
17秒前
LJJ发布了新的文献求助10
20秒前
Simlove完成签到,获得积分10
21秒前
高贵魂幽完成签到,获得积分10
21秒前
ccygpp199发布了新的文献求助10
23秒前
24秒前
整齐小松鼠完成签到,获得积分20
25秒前
Xw发布了新的文献求助10
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989334
求助须知:如何正确求助?哪些是违规求助? 3531428
关于积分的说明 11253936
捐赠科研通 3270119
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173