.png){kind=icon}
返回
Conditional invertible image re-scaling
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109459.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
One of the key issue for image re-scaling is modeling the down-sampling loss. The loss can be approached by a prior distribution through an invertible network in recent works. However, this assumption of independence between images and down-sampling losses is not always satisfied in practice. To address the above problem, we design a module to learn a latent variable representing the down-scaling loss conditional on low-resolution(LR) images according to the information entropy theory. Unlike previous methods, the down-scaling loss is recovered through the proposed module whose inputs are both LR images and predefined distributions. The difference between the high-resolution(HR) image and the low-resolution(LR) image is represented with a latent variable through a lossless invertible neural network. In addition, a conditional entropy loss is proposed to train the invertible neural network to suppress the conditional entropy between LR images and latent variables. It helps to decrease the effect of the latent variable to generate the HR image from LR images during the up-scaling procedure. We evaluate the proposed method on widely used data sets, and the experimental results demonstrate that our proposed method performs favorably against SOTA methods in terms of PSNR and SSIM metrics. (c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Invertible neural network
Image re-scaling
Information theory
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Single image super-resolution based on progressive fusion of orientation-aware features.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Single image super-resolution based on directional variance attention networkPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Multi-attention augmented network for single image super-resolution面向单幅图像超分辨率的多注意力增广网络PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Efficient deep neural network for photo-realistic image super-resolution一种高效的深度神经网络图像超分辨率算法PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏
查看更多内容