An All-in-One Network for Dehazing and Beyond

Abstract

This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level task performance on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN and training the joint pipeline from end to end, we witness a large improvement of the object detection performance on hazy images.

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Self-Tuned Deep Super Resolution
• Robust Emotion Recognition from Low Quality and Low Bit Rate Video: A Deep Learning Approach

Cited by in corpus (7)

• A Light Dual-Task Neural Network for Haze Removal
• Jointly Adversarial Network to Wavelength Compensation and Dehazing of Underwater Images
• Towards Domain Invariant Single Image Dehazing
• From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
• Single Image Dehazing Algorithm Based on Sky Region Segmentation
• Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze
• A De-raining semantic segmentation network for real-time foreground segmentation