Related papers: Toward Efficient Deep Blind RAW Image Restoration

Nowadays, many of the images captured are `observed' by machines only and not by humans, e.g., in autonomous systems. High-level machine vision models, such as object recognition or semantic segmentation, assume images are transformed into…

Current deep learning approaches in computer vision primarily focus on RGB data sacrificing information. In contrast, RAW images offer richer representation, which is crucial for precise recognition, particularly in challenging conditions…

Image recognition models that work in challenging environments (e.g., extremely dark, blurry, or high dynamic range conditions) must be useful. However, creating training datasets for such environments is expensive and hard due to the…

Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images do not necessarily model the genuine blurring process in…

Prior methodologies have disregarded the diversities among distinct degradation types during image reconstruction, employing a uniform network model to handle multiple deteriorations. Nevertheless, we discover that prevalent degradation…

In recent years, deep neural network-based restoration methods have achieved state-of-the-art results in various image deblurring tasks. However, one major drawback of deep learning-based deblurring networks is that large amounts of…

Denoising extreme low light images is a challenging task due to the high noise level. When the illumination is low, digital cameras increase the ISO (electronic gain) to amplify the brightness of captured data. However, this in turn…

Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task due to the unknown complex degradation of real-world images and the limited computation resources in practical applications. Recent research on…

Image restoration has been an extensively researched topic in numerous fields. With the advent of deep learning, a lot of the current algorithms were replaced by algorithms that are more flexible and robust. Deep networks have demonstrated…

This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original…

In this article, we address the challenges of image super-resolution and noise reduction, which are crucial for enhancing the quality of images derived from low-resolution or noisy data. We compared and assessed several approaches for…

Most super-resolution (SR) models struggle with real-world low-resolution (LR) images. This issue arises because the degradation characteristics in the synthetic datasets differ from those in real-world LR images. Since SR models are…

The performance of image super-resolution relies heavily on the accuracy of degradation information, especially under blind settings. Due to the absence of true degradation models in real-world scenarios, previous methods learn distinct…

Demosaicking and denoising are among the most crucial steps of modern digital camera pipelines and their joint treatment is a highly ill-posed inverse problem where at-least two-thirds of the information are missing and the rest are…

Super-resolution is a fundamental problem in computer vision which aims to overcome the spatial limitation of camera sensors. While significant progress has been made in single image super-resolution, most algorithms only perform well on…

Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is…

Existing neural networks for computer vision tasks are vulnerable to adversarial attacks: adding imperceptible perturbations to the input images can fool these methods to make a false prediction on an image that was correctly predicted…

Autonomous driving algorithms usually employ sRGB images as model input due to their compatibility with the human visual system. However, visually pleasing sRGB images are possibly sub-optimal for downstream tasks when compared to RAW…

Although the advances of self-supervised blind denoising are significantly superior to conventional approaches without clean supervision in synthetic noise scenarios, it shows poor quality in real-world images due to spatially correlated…

Recent developments in deep learning have revolutionized the paradigm of image restoration. However, its applications on real image denoising are still limited, due to its sensitivity to training data and the complex nature of real image…