This paper reviews the Challenge on Blind Enhancement of Compressed Image at NTIRE
2024 which aims at enhancing the quality of JPEG images which are compressed with …

Abstract Generative Adversarial Networks (GANs) have been widely used to recover vivid
textures in image super-resolution (SR) tasks. In particular one discriminator is utilized to …

This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times $4),
highlighting the solutions proposed and the outcomes obtained. The challenge involves …

Blind Compressed Image Restoration (CIR) has garnered significant attention due to its
practical applications. It aims to mitigate compression artifacts caused by unknown quality …

In this work, we investigate the understudied effect of the training data used for image super-
resolution (SR). Most commonly, novel SR methods are developed and benchmarked on …

Recently, considerable progress has been made in allin-one image restoration. Generally,
existing methods can be degradation-agnostic or degradation-aware. However, the former …

Diffusion models equipped with language models demonstrate excellent controllability in
image generation tasks, allowing image processing to adhere to human instructions …

Diffusion models significantly improve the quality of super-resolved images with their
impressive content generation capabilities. However, the huge computational costs limit the …

Deep Neural Networks (DNNs) require large amounts of annotated training data for a good
performance. Often this data is generated using manual labeling (error-prone and time …

Fast acquisition and generation of training data is an important problem for the training of
Deep Neural Networks (DNNs). Previous work using luminance keying for efficient training …