.png){kind=icon}
.png){kind=icon}
Return
Adaptive Multispectral Encoding Network for Image Demoireing
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2023.3280518.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Moire often appears when photographing textured objects, which can seriously degrade the quality of captured photographs. Due to the wide distribution of moire and the dynamic properties of moire, it is a challenge to effectively remove moire patterns. For this purpose, we present an adaptive multispectral encoding network (AMSDM) for image demoireing. In AMSDM, we leverage a multiscale network structure to process moire images at different spatial resolutions, which can relieve the issue of moire with distributed frequency spectrum. To solve the issue of dynamic properties of moire, we design an adaptive multispectral encoding (AMSE) module to encode moire patterns adaptively, which helps AMSDM restore moire images clearly. Besides, a demoireing convolutional network block (DMCNB) in the AMSE module makes AMSDM have the adaptability and the long-range correlation; thus, it can learn both global and local information about moire images. Extensive experimental results indicate that our proposed AMSDM significantly outperforms state-of-the-art (SOTA) methods and achieves a great balance between performance and efficiency.
Keywords:
Adaptive multispectral encoding (AMSE)
demoireing convolutional network block (DMCNB)
image demoireing
moire pattern
Journal
IF:
5.9
Papers:
1.9W
Citations:
5.8W