A number of super-resolution (SR) algorithms from in terpolation to deep neural networks
(DNN) have emerged to restore or create missing details of the input low-resolution image …

Most existing super-resolution methods do not perform well in real scenarios due to lack of
realistic training data and information loss of the model input. To solve the first problem, we …

The extremes of lighting (eg too much or too little light) usually cause many troubles for
machine and human vision. Many recent works have mainly focused on under-exposure …

Cameras capture sensor RAW images and transform them into pleasant RGB images,
suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous …

While raw images exhibit advantages over sRGB images (eg linearity and fine-grained
quantization level), they are not widely used by common users due to the large storage …

Harmonizing cut-and-paste images into perceptually realistic ones is challenging, as it
requires a full understanding of the discrepancies between the background of the target …

Most camera images are rendered and saved in the standard RGB (sRGB) format by the
camera's hardware. Due to the in-camera photo-finishing routines, nonlinear sRGB images …

Abstract sRGB images are now the predominant choice for pre-training visual models in
computer vision research, owing to their ease of acquisition and efficient storage …

Deep learning-based image compressors are actively being explored in an effort to
supersede conventional image compression algorithms, such as JPEG. Conventional and …

Most brands of modern consumer digital cameras nowadays are able to provide RAW-RGB
image pairs conveniently, even in the automatic mode. RAW images store pixel intensities …