Fog effect for photography using stereo vision

Li, Dongwei; Klette, Reinhard

doi:10.1007/s00371-014-1058-7

Cited by 8 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu [4] presents a haze-simulation method for photo editing using binocular stereo vision. Given a stereo pair, he estimates the depth information by stereo matching followed by a process to refine depth results for the given photo editing purpose.…”

Section: A Stereo Vision Haze-simulation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Image Hazing Algorithm Based on Generative Adversarial Networks

et al. 2020

View full text Add to dashboard Cite

Haze is an important factor in photography with a special aesthetic, emotional, or compositional meaning, an image hazing method is proposed based on generative adversarial network. The proposed network consists of two parts: the generator has a symmetric encoder and decoder structure with skip connection, which is used to generate hazy images; and the discriminator is a global fully convolutional network, which is used to identify the reality of the generated hazy images. The haze-free image is used as the input of the generative network to obtain a corresponding hazy image. Then the discriminative network judges the similarity between the original haze-free image and the corresponding hazy image to optimize the network parameters, which means that all the parameters of the entire network can be automatically learned through training. The loss function of the network is the combination of the GAN(Generative Adversarial Networks) loss and the REG(Regression) loss with a coefficient λ. We design a REG loss which includes feature loss loss FL and image loss loss IL. By calculating the loss, a model mapping the relationship between the two corresponding pixels from the original image and the synthetic hazy image respectively is well trained. In the last part of the paper, we have shown some impressing synthetic hazy images obtained by our model as well as analyzing the effects on images with different scenes. Moreover, we have contrasted the experimental results of our algorithm with that of other classical ones. Experiments demonstrate that the proposed algorithm has a better performance than other state-of-the-art methods on both virtual-scene and real-world images qualitatively and quantitatively. INDEX TERMS Generative adversarial networks, image hazing, regression loss, mapping from pixels to pixels.

show abstract

Section: A Stereo Vision Haze-simulation Methodsmentioning

confidence: 99%

“…So one way is to create a depth model. Liu [4] proposed a hazing method based on binocular stereo vision. However, taking account of stereo pairs, this method is too complicated.…”

Section: A Model-based Approachmentioning

confidence: 99%

Image Hazing Algorithm Based on Generative Adversarial Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The difference and novelty of these methods mainly lie on the depth estimation and the success of them heavily relies on the used auxiliary information, such as stereo pairs or manually annotation. For instance, [13] estimates the depth using binocular stereo vision. More specifically, they conduct stereo matching on the given stereo pairs to get the disparities which are further transformed into the depth using camera-intrinsic or camera-extrinsic parameters.…”

Section: Hazy Image Renderingmentioning

confidence: 99%

“…The pioneer image rendering methods often resort to the graphics techniques, e.g., geometry [27] or binocular vision [13]. In brief, the methods first reconstruct a 3D scene from a given 2D image and then synthesize the haze into the scene followed by 3D-to-2D flattening.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Neural Rendering for Image Hazing

Li,

Lin,

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two lesstouched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i.e., unpaired real hazy images. To this end, we propose a neural rendering method for image hazing, dubbed as HazeGEN. To be specific, HazeGEN is a knowledge-driven neural network which estimates the transmission map by leveraging a new prior, i.e., there exists the structure similarity (e.g., contour and luminance) between the transmission map and the input clean image. To adaptively learn the airlight, we build a neural module based on another new prior, i.e., the rendered hazy image and the exemplar are similar in the airlight distribution. To the best of our knowledge, this could be the first attempt to deeply rendering hazy images in an unsupervised fashion. Comparing with existing haze generation methods, HazeGEN renders the hazy images in an unsupervised, learnable, and controllable manner, thus avoiding the labor-intensive efforts in paired data collection and the domain-shift issue in haze generation. Extensive experiments show the promising performance of our method comparing with some baselines in both qualitative and quantitative comparisons. The code will be released on GitHub after acceptance.

show abstract

Star-Effect Simulation for Photography Using Self-calibrated Stereo Vision

Geng

Klette

2016

Image and Video Technology

View full text Add to dashboard Cite

Fog effect for photography using stereo vision

Cited by 8 publications

References 32 publications

Image Hazing Algorithm Based on Generative Adversarial Networks

Image Hazing Algorithm Based on Generative Adversarial Networks

Unsupervised Neural Rendering for Image Hazing

Star-Effect Simulation for Photography Using Self-calibrated Stereo Vision

Contact Info

Product

Resources

About