Deep learning architectures are now pervasive and filled almost all applications under
image processing, computer vision, and biometrics. The attractive property of feature …

Along with the massive growth of the Internet from the 1990s until now, various innovative
technologies have been created to bring users breathtaking experiences with more virtual …

Low-light image enhancement based on deep convolutional neural networks (CNNs) has
revealed prominent performance in recent years. However, it is still a challenging task since …

Background: Underwater images, in general, suffer from low contrast and high color
distortions due to the non-uniform attenuation of the light as it propagates through the water …

Recent transformer-based super-resolution (SR) methods have achieved promising results
against conventional CNN-based methods. However, these approaches suffer from …

Recently, Fourier frequency information has attracted much attention in Low-Light Image
Enhancement (LLIE). Some researchers noticed that, in the Fourier space, the lightness …

Due to light scatter and absorption in waterbody, underwater imaging can be easily impaired
with low contrast and visual distortion. The resulting images are often unable to meet the …

In this paper, we study the composed query image retrieval, which aims at retrieving the
target image similar to the composed query, ie, a reference image and the desired …

With the development of generative adversarial networks (GANs), recent face restoration
(FR) methods often utilize pre-trained GAN models (ie,, StyleGAN2) as prior to generate rich …

Many recent image restoration methods use Transformer as the backbone network and
redesign the Transformer blocks. Differently, we explore the parameter-sharing mechanism …