A generative adversarial network model fused with a self-attention mechanism for the super-resolution reconstruction of ancient murals.
Jianfang CaoXiaohui HuHongyan CuiYunchuan LiangZeyu ChenPublished in: IET Image Process. (2023)
Keyphrases
- network model
- super resolution reconstruction
- attention mechanism
- visual attention
- super resolution
- low resolution
- space time
- high resolution
- multi frame
- saliency map
- motion estimation
- generative model
- image super resolution
- visual attention model
- low resolution images
- high resolution images
- neural network
- image reconstruction
- vision system
- spatio temporal
- optical flow
- interpolation method
- eye movements
- high efficiency
- higher level
- image retrieval
- object recognition
- computer vision