Learning Dual Convolutional Neural Networks for Low-Level Vision

Citations Over TimeTop 10% of 2018 papers

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.

Related Papers

• → Spectral analysis of high resolution near-infrared spectra of ultra cool dwarfs(2007)16 cited
• → Anhydrous and Hydrated Protein Models Derived from High-Resolution and Low-Resolution Techniques(2012)2 cited
• → 151-P: A Case of A*24 Variant Showing Discrepancy Between High- and Low-Resolution HLA Typing Due to Complete Loss of All Introns(2010)
• → Synergies between low- and high-resolution spectroscopy of exoplanet atmospheres(2022)