In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two components of the target signals: structures and details. Motivated by this, our proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate the target signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated into existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.
@article{arxiv.1805.05020,
title = {Learning Dual Convolutional Neural Networks for Low-Level Vision},
author = {Jinshan Pan and Sifei Liu and Deqing Sun and Jiawei Zhang and Yang Liu and Jimmy Ren and Zechao Li and Jinhui Tang and Huchuan Lu and Yu-Wing Tai and Ming-Hsuan Yang},
journal= {arXiv preprint arXiv:1805.05020},
year = {2018}
}