人工智能
计算机科学
模式识别(心理学)
图像纹理
特征提取
计算机视觉
纹理合成
纹理压缩
编码器
纹理过滤
特征(语言学)
杠杆(统计)
匹配(统计)
纹理(宇宙学)
小波
图像(数学)
小波变换
掉期(金融)
人工神经网络
上下文图像分类
图像压缩
像素
特征向量
图像处理
Gabor滤波器
水准点(测量)
作者
Zhen Li,Zeng-Sheng Kuang,Zuo-Liang Zhu,Hong-Peng Wang,Xiu-Li Shao
标识
DOI:10.1109/tip.2022.3160072
摘要
Most reference-based image super-resolution (RefSR) methods directly leverage the raw features extracted from a pretrained VGG encoder to transfer the matched texture information from a reference image to a low-resolution image. We argue that simply operating on these raw features neglects the influence of irrelevant and redundant information and the importance of abundant high-frequency representations, leading to undesirable texture matching and transfer results. Taking the advantages of wavelet transformation, which represents the contextual and textural information of features at different scales, we propose a Wavelet-based Texture Reformation Network (WTRN) for RefSR. We first decompose the extracted texture features into low-frequency and high-frequency sub-bands and conduct feature matching on the low-frequency component. Based on the correlation map obtained from the feature matching process, we then separately swap and transfer wavelet-domain features at different stages of the network. Furthermore, a wavelet-based texture adversarial loss is proposed to make the network generate more visually plausible textures. Experiments on four benchmark datasets demonstrate that our proposed method outperforms previous RefSR methods both quantitatively and qualitatively. The source code is available at https://github.com/zskuang58/WTRN-TIP.
科研通智能强力驱动
Strongly Powered by AbleSci AI