计算机科学
人工智能
特征(语言学)
代表(政治)
能见度
特征学习
编码(集合论)
网(多面体)
图像(数学)
可视化
模式识别(心理学)
计算机视觉
哲学
几何学
语言学
物理
数学
光学
集合(抽象数据类型)
政治
政治学
法学
程序设计语言
作者
Jiafeng Li,Yaopeng Li,Zhuo Li,Lingyan Kuang,Tianjian Yu
标识
DOI:10.1109/tmm.2022.3163554
摘要
Captured images of outdoor scenes usually exhibit low visibility in cases of severe haze, which interferes with optical imaging and degrades image quality. Most of the existing methods solve the single-image dehazing problem by applying supervised training on paired images; however, in practice, the pairing of real-world images is not viable. Additionally, the processing speed of individual dehazing models is important in practical applications. In this study, a novel unsupervised single image dehazing network (USID-Net) based on disentangled representations without paired training images is explored. Furthermore, considering the trade-off between performance and memory storage, a compact multi-scale feature attention (MFA) module is developed, integrating multi-scale feature representation and attention mechanism to facilitate feature representation. To effectively extract haze information, a mechanism referred to as OctEncoder is designed to include multi-frequency representations that can capture more global information. Extensive experiments show that USID-Net achieves competitive dehazing results and a relatively high processing speed compared to state-of-the-art methods. The source code is available at https://github.com/dehazing/USID-Net .
科研通智能强力驱动
Strongly Powered by AbleSci AI