Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior

Zhang, Jing; Cao, Yang; Fang, Shuai; Kang, Yu; Chen, Chang Wen

doi:10.1109/cvpr.2017.742

Cited by 143 publications

(147 citation statements)

References 26 publications

Supporting

Mentioning

143

Contrasting

Unclassified

Order By: Relevance

“…Usually, given the observation y, one need to estimate x and z, which is an ill-posed inverse problem. Different statistical methods have been proposed by enforcing statistical regularities on the unknown variables [5,9,18,22,38,40,43] and obtain the estimates by using MAP (Maximum A Posteriori) estimation. Mathematically, it can be formulated as:…”

Section: Proposed Methods 31 Problem Formulationmentioning

confidence: 99%

“…For example, many color constancy algorithms work by assuming some regularities in the colors of natural objects viewed under canonical illumination, e.g., gray world [9], gray edge [38], and shades of gray [18]. Besides, by assuming that the surface shading and scene transmission are locally uncorrelated, most of single image dehazing methods are proposed based on various image priors, e.g., color attenuation [43], dark channel [22,23], haze line [5] and maximum reflectance prior [40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images

Zhang

Cao

Wang

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Modeling statistical regularity plays an essential role in ill-posed image processing problems. Recently, deep learning based methods have been presented to implicitly learn statistical representation of pixel distributions in natural images and leverage it as a constraint to facilitate subsequent tasks, such as color constancy and image dehazing. However, the existing CNN architecture is prone to variability and diversity of pixel intensity within and between local regions, which may result in inaccurate statistical representation. To address this problem, this paper presents a novel fully point-wise CNN architecture for modeling statistical regularities in natural images. Specifically, we propose to randomly shuffle the pixels in the origin images and leverage the shuffled image as input to make CNN more concerned with the statistical properties. Moreover, since the pixels in the shuffled image are independent identically distributed, we can replace all the large convolution kernels in CNN with point-wise (1 * 1) convolution kernels while maintaining the representation ability. Experimental results on two applications: color constancy and image dehazing, demonstrate the superiority of our proposed network over the existing architectures, i.e., using 1/10∼1/100 network parameters and computational cost while achieving comparable performance.

show abstract

Section: Proposed Methods 31 Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images

Zhang

Cao

Wang

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…As discussed earlier, for many kinds of image degradations, many researches have been conducted to remove/reduce the degradation to restore the underlying clear images [15], [16], [17], [18], [19], [20], [21], [22], [25], [37], [38], [40], [42], [44], [45]. One interesting problem is whether we can get better classification accuracy by training the CNN classifiers on the clear images, and testing on the restored test images after the degradation removal.…”

Section: F Does Degradation-removal Pre-processing Help?mentioning

confidence: 99%

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Pei

Huang

Zou

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

180

View full text Add to dashboard Cite

Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep-learning neural networks, especially the Convolutional Neural Networks (CNN). Most of the existing works are focused on classifying very clear natural images, evidenced by the widely used image databases such as Caltech-256, PASCAL VOCs and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification. More specifically, we wonder whether image-classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image-classification performance. In this paper, we empirically study this problem for four kinds of degraded images -hazy images, underwater images, motion-blurred images and fish-eye images. For this study, we synthesize a large number of such degraded images by applying respective physical models to the clear natural images and collect a new hazy image dataset from the Internet. We expect this work can draw more interests from the community to study the classification of degraded images.

show abstract

“…For example, in [16], a method was developed to remove the nighttime haze with glow and multiple light colors. In [32], a fast haze removal method was proposed for nighttime images using the maximum reflectance prior.…”

Section: Related Workmentioning

confidence: 99%

Does Haze Removal Help CNN-Based Image Classification?

Pei

Huang

Zou

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Hazy images are common in real scenarios and many dehazing methods have been developed to automatically remove the haze from images. Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images. When the ground-truth haze-free image is available for a hazy image, quantitative evaluation of image dehazing is usually based on objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). However, in many applications, large-scale images are collected not for visual examination by human. Instead, they are used for many high-level vision tasks, such as automatic classification, recognition and categorization. One fundamental problem here is whether various dehazing methods can produce clearer images that can help improve the performance of the high-level tasks. In this paper, we empirically study this problem in the important task of image classification by using both synthetic and real hazy image datasets. From the experimental results, we find that the existing image-dehazing methods cannot improve much the image-classification performance and sometimes even reduce the image-classification performance.

show abstract

Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior

Cited by 143 publications

References 26 publications

Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images

Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification

Does Haze Removal Help CNN-Based Image Classification?

Contact Info

Product

Resources

About