Dual Convolutional Neural Networks for Low-Level Vision

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 estimating two components of the target signals: structures and details. Motivated by this, we design the proposed DualCNN to have two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate desired 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 that have been specially designed for each individual task.