Meiya Chen

TL;DR: This paper presents a two-stage deep convolutional neural network to model both the noise and the medical image simultaneously and introduces both the short-term and long-term connections in the network which could promote the information propagation between different layers efficiently.

TL;DR: This article provides a comprehensive analysis of existing destriping methods and proposes a deep convolutional neural network (CNN) for handling various kinds of stripes, designed to simultaneously model the stripe and image, which better facilitates distinguishing them from each other.

TL;DR: The NTIRE 2022 challenge on burst super-resolution is reviewed, with the top performing methods establishing a new state-of-the-art on the burstsuper-resolution task.

TL;DR: This work discovers that the noise level and the denoiser is tightly coupled, and proposes efficient blind denoising convolutional neural network (BDCNN) consisting of two stages: a down-sampling regression network for estimating noiselevel and a fully Convolutional network for denoises, such that it could adaptively handle the unknown noise level during iteration.

TL;DR: Zhang et al. as discussed by the authors proposed a direction and residual awareness network within the curriculum learning paradigm for the rain streaks' removal, in which the principal directionality property endows us with the discriminative representation ability of better differing rain streaks from image edges.