Learning Dual Convolutional Neural Networks for Low-Level Vision

Abstract

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.

arXiv commentCVPR 2018

References in corpus (5)

• Deep Residual Learning for Image Recognition
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Clearing the Skies: A deep network architecture for single-image rain removal
• Image De-raining Using a Conditional Generative Adversarial Network
• Deeply-Recursive Convolutional Network for Image Super-Resolution

Cited by in corpus (6)

• Single Image Deraining: From Model-Based to Data-Driven and Beyond
• Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
• Robust X-ray Sparse-view Phase Tomography via Hierarchical Synthesis Convolutional Neural Networks
• Gradient Information Guided Deraining with A Novel Network and Adversarial Training
• Residual Squeeze-and-Excitation Network for Fast Image Deraining
• Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision