The last decade has seen an astronomical shift from imaging with DSLR and point-and-
shoot cameras to imaging with smartphone cameras. Due to the small aperture and sensor …

Abstract Machine learning techniques work best when the data used for training resembles
the data used for evaluation. This holds true for learned single-image denoising algorithms …

Lacking realistic ground truth data, image denoising techniques are traditionally evaluated
on images corrupted by synthesized iid Gaussian noise. We aim to obviate this unrealistic …

High-frequency regions like edges compromise the image denoising performance. In
traditional hand-crafted systems, image edges/textures were regularly used to restore the …

The availability of large-scale datasets has helped unleash the true potential of deep
convolutional neural networks (CNNs). However, for the single-image denoising problem …

Deep learning-based image denoising approaches have been extensively studied in recent
years, prevailing in many public benchmark datasets. However, the stat-of-the-art networks …

The lack of large-scale real raw image denoising dataset gives the rise to challenges on
synthesizing realistic raw image noise for training denoising models. However, the real raw …

Deep convolutional neural networks perform better on images containing spatially invariant
noise (synthetic noise); however, its performance is limited on real-noisy photographs and …

Recently, self-supervised neural networks have shown excellent image denoising
performance. However, current dataset free methods are either computationally expensive …

The lack of large-scale noisy-clean image pairs restricts supervised denoising methods'
deployment in actual applications. While existing unsupervised methods are able to learn …