A Light Dual-Task Neural Network for Haze Removal

Abstract

Single-image dehazing is a challenging problem due to its ill-posed nature. Existing methods rely on a suboptimal two-step approach, where an intermediate product like a depth map is estimated, based on which the haze-free image is subsequently generated using an artificial prior formula. In this paper, we propose a light dual-task Neural Network called LDTNet that restores the haze-free image in one shot. We use transmission map estimation as an auxiliary task to assist the main task, haze removal, in feature extraction and to enhance the generalization of the network. In LDTNet, the haze-free image and the transmission map are produced simultaneously. As a result, the artificial prior is reduced to the smallest extent. Extensive experiments demonstrate that our algorithm achieves superior performance against the state-of-the-art methods on both synthetic and real-world images.

6 pages, 4 figures

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• TensorFlow: A system for large-scale machine learning
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Deep Learning Face Representation by Joint Identification-Verification
• Deep Voice: Real-time Neural Text-to-Speech
• Text-Attentional Convolutional Neural Networks for Scene Text Detection
• An All-in-One Network for Dehazing and Beyond
• TensorLayer: A Versatile Library for Efficient Deep Learning Development
• Predicting People's 3D Poses from Short Sequences