Blind-spot network (BSN) and its variants have made significant advances in self-supervised
denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical …

Recently, significant progress has been made on image denoising with strong supervision
from large-scale datasets. However, obtaining well-aligned noisy-clean training image pairs …

Plug-and-Play methods constitute a class of iterative algorithms for imaging problems where
regularization is performed by an off-the-shelf denoiser. Although Plug-and-Play methods …

Learning-based image denoising methods have been bounded to situations where well-
aligned noisy and clean images are given, or samples are synthesized from predetermined …

Since the introduction of adaptive steganography, most of the recent research works seek at
designing cost functions that are evaluated against steganalysis methods. While those …

Crack detection is an important task to monitor the structural health of the infrastructure
exposed to fire. The manual inspections are time consuming and the outcome depends on …

In this work, we propose a framework to learn a local regularization model for solving
general image restoration problems. This regularizer is defined with a fully convolutional …

Color image restoration methods typically represent images as vectors in Euclidean space
or combinations of three monochrome channels. However, they often overlook the …

Multi-photon laser scanning microscopy is an advantageous technique for layered imaging
in thick tissue samples. It enables reduced phototoxicity as the region of fluorescence …

Speckle noise has long been an extensively studied problem in medical imaging. In recent
years, there have been significant advances in leveraging deep learning methods for noise …