Single Image Haze Removal using a Generative Adversarial Network
Traditional methods to remove haze from images rely on estimating a transmission map. When dealing with single images, this becomes an ill-posed problem due to the lack of depth information. In this paper, we propose an end-to-end learning based approach which uses a modified conditional Generative Adversarial Network to directly remove haze from an image. We employ the usage of the Tiramisu model in place of the classic U-Net model as the generator owing to its higher parameter efficiency and performance. Moreover, a patch based discriminator was used to reduce artefacts in the output. To further improve the perceptual quality of the output, a hybrid weighted loss function was designed and used to train the model. Experiments on synthetic and real world hazy images demonstrates that our model performs competitively with the state of the art methods.
Code (2)
Tasks
Generative Adversarial NetworkImage DehazingSingle Image Haze RemovalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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. The existing haze removal methods in literature, including the recently introduced deep learning methods, model the problem of haze removal as that o…
Single Image Haze RemovalSingle Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
We present a method to restore a clear image from a haze-affected image using a Wasserstein generative adversarial network. As the problem is ill-conditioned, previous methods have required a prior on natural images or m…
Generative Adversarial NetworkImage DehazingSingle Image Haze RemovalPMHLD: Patch Map Based Hybrid Learning DehazeNet for Single Image Haze Removal
Images captured in a hazy environment usually suffer from bad visibility and missing information. Over many years, learning-based and handcrafted prior-based dehazing algorithms have been rigorously developed. However, b…
Computational PhenotypingDenoisingGenerative Adversarial NetworkImage Dehazing+5See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
The issue of image haze removal has attracted wide attention in recent years. However, most existing haze removal methods cannot restore the scene with clear blue sky, since the color and texture information of the objec…
Generative Adversarial NetworkCGGAN: A Context Guided Generative Adversarial Network For Single Image Dehazing
Image haze removal is highly desired for the application of computer vision. This paper proposes a novel Context Guided Generative Adversarial Network (CGGAN) for single image dehazing. Of which, an novel new encoder-dec…
DecoderGenerative Adversarial NetworkImage DehazingSingle Image Dehazing