FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing

01/20/2020
by   Yu Dong, et al.
16

Recently, convolutional neural networks (CNNs) have achieved great improvements in single image dehazing and attained much attention in research. Most existing learning-based dehazing methods are not fully end-to-end, which still follow the traditional dehazing procedure: first estimate the medium transmission and the atmospheric light, then recover the haze-free image based on the atmospheric scattering model. However, in practice, due to lack of priors and constraints, it is hard to precisely estimate these intermediate parameters. Inaccurate estimation further degrades the performance of dehazing, resulting in artifacts, color distortion and insufficient haze removal. To address this, we propose a fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing. With the proposed Fusion-discriminator which takes frequency information as additional priors, our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts. Moreover, we synthesize a large-scale training dataset including various indoor and outdoor hazy images to boost the performance and we reveal that for learning-based dehazing methods, the performance is strictly influenced by the training data. Experiments have shown that our method reaches state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 6

page 7

page 10

page 11

research
01/09/2018

CANDY: Conditional Adversarial Networks based Fully End-to-End System for Single Image Haze Removal

Single image haze removal is a very challenging and ill-posed problem. T...
research
05/03/2018

Perceptually Optimized Generative Adversarial Network for Single Image Dehazing

Existing approaches towards single image dehazing including both model-b...
research
01/28/2016

DehazeNet: An End-to-End System for Single Image Haze Removal

Single image haze removal is a challenging ill-posed problem. Existing m...
research
08/25/2021

Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

In recent years, single image dehazing models (SIDM) based on atmospheri...
research
02/19/2021

A GAN-Based Input-Size Flexibility Model for Single Image Dehazing

Image-to-image translation based on generative adversarial network (GAN)...
research
12/07/2017

Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal

Understanding shadows from a single image spontaneously derives into two...
research
01/13/2023

Short-time SSVEP data extension by a novel generative adversarial networks based framework

Steady-state visual evoked potentials (SSVEPs) based brain-computer inte...

Please sign up or login with your details

Forgot password? Click here to reset