Proceedings ArticleDOI
Non-local Image Dehazing
Dana Berman,Tali Treibitz,Shai Avidan +2 more
- pp 1674-1682
TLDR
This work proposes an algorithm, linear in the size of the image, deterministic and requires no training, that performs well on a wide variety of images and is competitive with other state-of-the-art methods on the single image dehazing problem.Abstract:
Haze limits visibility and reduces image contrast in outdoor images. The degradation is different for every pixel and depends on the distance of the scene point from the camera. This dependency is expressed in the transmission coefficients, that control the scene attenuation and amount of haze in every pixel. Previous methods solve the single image dehazing problem using various patch-based priors. We, on the other hand, propose an algorithm based on a new, non-local prior. The algorithm relies on the assumption that colors of a haze-free image are well approximated by a few hundred distinct colors, that form tight clusters in RGB space. Our key observation is that pixels in a given cluster are often non-local, i.e., they are spread over the entire image plane and are located at different distances from the camera. In the presence of haze these varying distances translate to different transmission coefficients. Therefore, each color cluster in the clear image becomes a line in RGB space, that we term a haze-line. Using these haze-lines, our algorithm recovers both the distance map and the haze-free image. The algorithm is linear in the size of the image, deterministic and requires no training. It performs well on a wide variety of images and is competitive with other stateof-the-art methods.read more
Citations
More filters
Posted Content
Physics-Based Generative Adversarial Models for Image Restoration and Beyond
Jinshan Pan,Jiangxin Dong,Yang Liu,Jiawei Zhang,Jimmy Ren,Jinhui Tang,Yu-Wing Tai,Ming-Hsuan Yang +7 more
TL;DR: Zhang et al. as discussed by the authors proposed a physics model constrained learning algorithm to guide the estimation of the specific task in the conventional GAN framework, which can be applied to a variety of image restoration and related low-level vision problems.
Journal ArticleDOI
Deep Energy: Task Driven Training of Deep Neural Networks
TL;DR: This work dives into the regime of Deep-Energy, a task-driven training approach that substitutes the generic loss with minimization of energy functions using DNNs, showing clear benefits of both speedup and improved accuracy versus the classical energy minimization approach, and competitive performance with respect to fully supervised alternatives.
Posted Content
Effects of Image Degradations to CNN-based Image Classification.
TL;DR: This paper empirically studies 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.
Proceedings ArticleDOI
Unsupervised Conditional Disentangle Network For Image Dehazing
TL;DR: This work proposes an Unsupervised Conditional Disentangle Network (UCDN) using unpaired dataset and enforces the constraint by introducing physical-based disentanglement, which adapts the multi-concentration of fog and outperforms on the dataset with different concentrations.
Proceedings ArticleDOI
Non-blind Image Restoration Based on Convolutional Neural Network
TL;DR: Wang et al. as mentioned in this paper proposed a non-blind CNN-based image restoration processor, aiming to be robust against a perturbation of the degradation model compared to the blind restoration processor.
References
More filters
Proceedings ArticleDOI
Visibility in bad weather from a single image
TL;DR: A cost function in the framework of Markov random fields is developed, which can be efficiently optimized by various techniques, such as graph-cuts or belief propagation, and is applicable for both color and gray images.
Journal ArticleDOI
Single image dehazing
TL;DR: Results demonstrate the new method abilities to remove the haze layer as well as provide a reliable transmission estimate which can be used for additional applications such as image refocusing and novel view synthesis.
Proceedings ArticleDOI
Fast visibility restoration from a single color or gray level image
TL;DR: A novel algorithm and variants for visibility restoration from a single image which allows visibility restoration to be applied for the first time within real-time processing applications such as sign, lane-marking and obstacle detection from an in-vehicle camera.
Proceedings ArticleDOI
Single image haze removal using dark channel prior
Kaiming He,Jian Sun,Xiaoou Tang +2 more
TL;DR: A simple but effective image prior - dark channel prior to remove haze from a single input image is proposed, based on a key observation - most local patches in haze-free outdoor images contain some pixels which have very low intensities in at least one color channel.
Journal ArticleDOI
Dehazing Using Color-Lines
TL;DR: A new method for single-image dehazing that relies on a generic regularity in natural images where pixels of small image patches typically exhibit a 1D distribution in RGB color space, known as color-lines is described.