.png){kind=icon}
.png){kind=icon}
Return
Multibranch Wavelet-Based Network for Image Demoiréing
.png){kind=icon}
OA
AI
DOI：10.3390/s24092762.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Moir & eacute; patterns caused by aliasing between the camera's sensor and the monitor can severely degrade image quality. Image demoir & eacute;ing is a multi-task image restoration method that includes texture and color restoration. This paper proposes a new multibranch wavelet-based image demoir & eacute;ing network (MBWDN) for moir & eacute; pattern removal. Moir & eacute; images are separated into sub-band images using wavelet decomposition, and demoir & eacute;ing can be achieved using the different learning strategies of two networks: moir & eacute; removal network (MRN) and detail-enhanced moir & eacute; removal network (DMRN). MRN removes moir & eacute; patterns from low-frequency images while preserving the structure of smooth areas. DMRN simultaneously removes high-frequency moir & eacute; patterns and enhances fine details in images. Wavelet decomposition is used to replace traditional upsampling, and max pooling effectively increases the receptive field of the network without losing the spatial information. Through decomposing the moir & eacute; image into different levels using wavelet transform, the feature learning results of each branch can be fully preserved and fed into the next branch; therefore, possible distortions in the recovered image are avoided. Thanks to the separation of high- and low-frequency images during feature training, the proposed two networks achieve impressive moir & eacute; removal effects. Based on extensive experiments conducted using public datasets, the proposed method shows good demoir & eacute;ing validity both quantitatively and qualitatively when compared with the state-of-the-art approaches.
Keywords:
moir & eacute
pattern
wavelet transform
deep learning
image restoration
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.