Ruofan Zhou

TL;DR: This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.

TL;DR: The proposed KMSR consists of two stages: a pool of realistic blur-kernels with a generative adversarial network (GAN) and then a super-resolution network with HR and corresponding LR images constructed with the generated kernels that incorporates blur-kernel modeling in the training.

TL;DR: This work presents a novel dataset, the Virtual Image Dataset for Illumination Transfer (VIDIT), in an effort to create a reference evaluation benchmark and to push forward the development of illumination manipulation methods.

TL;DR: The AIM 2020 challenge on virtual image relighting and illumination estimation as discussed by the authors focused on one-to-one relighting, where the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation.

TL;DR: In this paper, a deep residual network is proposed to learn an end-to-end mapping between Bayer images and high-resolution images, which can recover high-quality super-resolved images from low-resolution Bayer mosaics in a single step without producing the artifacts common to such processing when the two operations are done separately.