HDP-Net: Haze Density Prediction Network for Nighttime Dehazing

Liao, Yinghong; Su, Zhuo; Liang, Xiangguo; Qiu, Bin

doi:10.1007/978-3-030-00776-8_43

Cited by 20 publications

(26 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To quantify the dehazing results, we pick out the low‐light haze‐free images and the corresponding synthesized hazy images in the website http://www.flickr.com and Liao's paper [44] for the test. Table 1 shows the blind assessment values and Brisque of our proposed and other methods achieved by measuring the real‐world images from Figures 9 to 14.…”

Section: Experiments Resultsmentioning

confidence: 99%

Low‐light image haze removal with light segmentation and nonlinear image depth estimation

Qian

Bao

2022

IET Image Processing

View full text Add to dashboard Cite

Hazy image obtained in the low-light environment has the characteristics of low contrast, non-uniform illumination, color cast and much noise. In this paper, a method is put forward which can be properly applied to recover low-light hazy images. The original image is first decomposed into glow layer and haze layer with a modified color channel transformation for glow artifacts and color balanced. A new light segmentation function is proposed next by using gamma correction of channel difference and setting threshold levels to determine if the pixel belongs to light source regions. Then the ambient illuminance map is estimated using maximum reflectance prior to computing the atmosphere light in the light and non-light regions. Finally, a novel nonlinear image depth estimation model is established to build the relationship between the image depth map and three image features including luminance, saturation and gradient map for the light areas. The experimental results prove that the dehazing algorithm is reliable for removing haze and glow artifacts of active light sources, reducing much noise and improving the visibility.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Low‐light image haze removal with light segmentation and nonlinear image depth estimation

Qian

Bao

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Due to the problems of the training set and the network architecture itself, the dehazing algorithm based on deep learning has a certain deviation in the estimation of the transmission map, which makes it impossible to obtain a satisfactory dehazing effect for some scenes when dehazing the real hazy image. Unlike some of the abovementioned methods that use CNN to estimate the transmission, Liao et al [ 20 ] used CNN to predict the haze density of the image and then subtracted the predicted haze density from the hazy image to obtain a clean image. Dong et al [ 21 ] proposed a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion (MSBDN).…”

Section: Related Workmentioning

confidence: 99%

“…Recently, the end-to-end image dehazing method [ 20 , 21 , 22 ] provides a new idea, which inputs the hazy image into the network to obtain the clean image directly. In the end-to-end dehazing algorithm based on deep learning, a larger receptive field can extract more information in the image, to better extract the overall image and the relationship features between adjacent pixels, and better predict clean images.…”

Section: Introductionmentioning

confidence: 99%

High-Resolution Representations Network for Single Image Dehazing

Han

Zhu

et al. 2022

Sensors

View full text Add to dashboard Cite

Deep learning-based image dehazing methods have made great progress, but there are still many problems such as inaccurate model parameter estimation and preserving spatial information in the U-Net-based architecture. To address these problems, we propose an image dehazing network based on the high-resolution network, called DeHRNet. The high-resolution network originally used for human pose estimation. In this paper, we make a simple yet effective modification to the network and apply it to image dehazing. We add a new stage to the original network to make it better for image dehazing. The newly added stage collects the feature map representations of all branches of the network by up-sampling to enhance the high-resolution representations instead of only taking the feature maps of the high-resolution branches, which makes the restored clean images more natural. The final experimental results show that DeHRNet achieves superior performance over existing dehazing methods in synthesized and natural hazy images.

show abstract

“…The fusion based methods combined a group of images into a single one while only keeping the most remarkable feature of each image. Ancuti et al [29,30] proposed an effective algorithm based on fusion for nighttime haze removal. The atmospheric light component is estimated on the image patch instead of the entire image.…”

Section: Related Workmentioning

confidence: 99%

Nighttime image dehazing using color cast removal and dual path multi-scale fusion strategy

Wang

Wei

et al. 2021

Front. Comput. Sci.

View full text Add to dashboard Cite

Nighttime image dehazing aims to remove the effect of haze on the images captured in nighttime, which however, raises new challenges such as severe color distortion, more complex lighting conditions, and lower contrast. Instead of estimating the transmission map and atmospheric light that are difficult to be accurately acquired in nighttime, we propose a nighttime image dehazing method composed of a color cast removal and a dual path multi-scale fusion algorithm. We first propose a human visual system (HVS) inspired color correction model, which is effective for removing the color deviation on nighttime hazy images. Then, we propose to use dual path strategy that includes an underexposure and a contrast enhancement path for multi-scale fusion, where the weight maps are achieved by selecting appropriate exposed areas under Gaussian pyramids. Extensive experiments demonstrate that the visual effect of the hazy nighttime images in real-world datasets can be significantly improved by our method regarding contrast, color fidelity, and visibility. In addition, our method outperforms the state-of-the-art methods qualitatively and quantitatively.

show abstract

HDP-Net: Haze Density Prediction Network for Nighttime Dehazing

Cited by 20 publications

References 12 publications

Low‐light image haze removal with light segmentation and nonlinear image depth estimation

Low‐light image haze removal with light segmentation and nonlinear image depth estimation

High-Resolution Representations Network for Single Image Dehazing

Nighttime image dehazing using color cast removal and dual path multi-scale fusion strategy

Contact Info

Product

Resources

About