Passive imaging through intense atmospheric scattering is a critical yet formidable challenge in optical imaging,with profound implications across various applications.Conventional cameras struggle under severe scatte...Passive imaging through intense atmospheric scattering is a critical yet formidable challenge in optical imaging,with profound implications across various applications.Conventional cameras struggle under severe scattering conditions,fundamentally limiting their effectiveness.We propose a groundbreaking directional atmospheric scattering model that revolutionizes passive imaging capabilities,converting a conventional camera to a super-camera.The model precisely characterizes directional photon propagation through scattering media,transforming this historically ill-posed problem into a well-posed solution,based on which a 4D spatial-angular scattering reconstruction method is proposed,which leverages both ballistic photons and directionally resolved scattered light,without relying on any scene-specific priors,to achieve unprecedented passive imaging performance enabling color imaging through over 12 transport mean free paths at distances up to 1.76 km.Our system recovers targets contributing as little as 0.00016%of the total detected signal,enhancing a standard camera’s signal recovery capacity by nearly 200×.To validate our approach,we introduce the first-ever real-world multiperspective scattering dataset,providing a critical benchmark for future research.We mark a paradigm shift in passive imaging,offering transformative potential for real-world applications under extreme atmospheric scattering conditions.展开更多
This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside ...This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside monitoring.It adopts two networks:one is generator(G),and the other is discriminator(D).The G adopts the U-Net architecture,whose layers are particularly designed to incorporate the atmospheric scattering model of image dehazing.By using a reformulated atmospheric scattering model,the weights of the generator network are initialized by the coarse transmission map,and the biases are adaptively adjusted by using the previous round's trained weights.Since the details may be blurry after the fog is removed,the contrast loss is added to enhance the visibility actively.Aside from the typical GAN adversarial loss,the pixel-wise Mean Square Error(MSE)loss,the contrast loss and the dark channel loss are introduced into the generator loss function.Extensive experiments on benchmark images,the results of which are compared with those of several state-of-the-art methods,demonstrate that the proposed DehazeGAN performs better and is more effective.展开更多
Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by ...Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by human vision and by some outdoor computer vision systems.Therefore image dehazing is an important issue and has been widely researched in the field of computer vision.The role of image dehazing is to remove the influence of weather factors in order to improve the visual effects of the image and provide benefit to post-processing.This paper reviews the main techniques of image dehazing that have been developed over the past decade.Firstly,we innovatively divide a number of approaches into three categories:image enhancement based methods,image fusion based methods and image restoration based methods.All methods are analyzed and corresponding sub-categories are introduced according to principles and characteristics.Various quality evaluation methods are then described,sorted and discussed in detail.Finally,research progress is summarized and future research directions are suggested.展开更多
Due to the presence of turbid media, such as microdust and water vapor in the environment, outdoor pictures taken under hazy weather circumstances are typically degraded. To enhance the quality of such images, this wo...Due to the presence of turbid media, such as microdust and water vapor in the environment, outdoor pictures taken under hazy weather circumstances are typically degraded. To enhance the quality of such images, this work proposes a new hybrid λ2-λ0 penalty model for image dehazing. This model performs a weighted fusion of two distinct transmission maps, generated by imposing λ2 and λ0 norm penalties on the approximate regression coefficients of the transmission map. This approach effectively balances the sparsity and smoothness associated with the λ0 and λ2 norms, thereby optimizing the transmittance map. Specifically, when the λ2 norm is penalized in the model, an updated guided image is obtained after implementing λ0 penalty. The resulting optimization problem is effectively solved using the least square method and the alternating direction algorithm. The dehazing framework combines the advantages of λ2 and λ0 norms, enhancing sparse and smoothness, resulting in higher quality images with clearer details and preserved edges.展开更多
基金supported by the Shenzhen Science and Technology Project,China(Grant No.KCXFZ20240903094301003).
文摘Passive imaging through intense atmospheric scattering is a critical yet formidable challenge in optical imaging,with profound implications across various applications.Conventional cameras struggle under severe scattering conditions,fundamentally limiting their effectiveness.We propose a groundbreaking directional atmospheric scattering model that revolutionizes passive imaging capabilities,converting a conventional camera to a super-camera.The model precisely characterizes directional photon propagation through scattering media,transforming this historically ill-posed problem into a well-posed solution,based on which a 4D spatial-angular scattering reconstruction method is proposed,which leverages both ballistic photons and directionally resolved scattered light,without relying on any scene-specific priors,to achieve unprecedented passive imaging performance enabling color imaging through over 12 transport mean free paths at distances up to 1.76 km.Our system recovers targets contributing as little as 0.00016%of the total detected signal,enhancing a standard camera’s signal recovery capacity by nearly 200×.To validate our approach,we introduce the first-ever real-world multiperspective scattering dataset,providing a critical benchmark for future research.We mark a paradigm shift in passive imaging,offering transformative potential for real-world applications under extreme atmospheric scattering conditions.
基金This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(grant number NRF-2018R1D1A1B07043331).
文摘This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside monitoring.It adopts two networks:one is generator(G),and the other is discriminator(D).The G adopts the U-Net architecture,whose layers are particularly designed to incorporate the atmospheric scattering model of image dehazing.By using a reformulated atmospheric scattering model,the weights of the generator network are initialized by the coarse transmission map,and the biases are adaptively adjusted by using the previous round's trained weights.Since the details may be blurry after the fog is removed,the contrast loss is added to enhance the visibility actively.Aside from the typical GAN adversarial loss,the pixel-wise Mean Square Error(MSE)loss,the contrast loss and the dark channel loss are introduced into the generator loss function.Extensive experiments on benchmark images,the results of which are compared with those of several state-of-the-art methods,demonstrate that the proposed DehazeGAN performs better and is more effective.
基金supported by the National Natural Science Foundation of China(61403283)Shandong Provincial Natural Science Foundation(ZR2013FQ036.ZR2015PE025)+2 种基金the Spark Program of China(2013GA740053)the Spark Program of Shandong Province(2013XH06034)the Technology Development Plan of Weifang City(201301015)
文摘Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by human vision and by some outdoor computer vision systems.Therefore image dehazing is an important issue and has been widely researched in the field of computer vision.The role of image dehazing is to remove the influence of weather factors in order to improve the visual effects of the image and provide benefit to post-processing.This paper reviews the main techniques of image dehazing that have been developed over the past decade.Firstly,we innovatively divide a number of approaches into three categories:image enhancement based methods,image fusion based methods and image restoration based methods.All methods are analyzed and corresponding sub-categories are introduced according to principles and characteristics.Various quality evaluation methods are then described,sorted and discussed in detail.Finally,research progress is summarized and future research directions are suggested.
文摘Due to the presence of turbid media, such as microdust and water vapor in the environment, outdoor pictures taken under hazy weather circumstances are typically degraded. To enhance the quality of such images, this work proposes a new hybrid λ2-λ0 penalty model for image dehazing. This model performs a weighted fusion of two distinct transmission maps, generated by imposing λ2 and λ0 norm penalties on the approximate regression coefficients of the transmission map. This approach effectively balances the sparsity and smoothness associated with the λ0 and λ2 norms, thereby optimizing the transmittance map. Specifically, when the λ2 norm is penalized in the model, an updated guided image is obtained after implementing λ0 penalty. The resulting optimization problem is effectively solved using the least square method and the alternating direction algorithm. The dehazing framework combines the advantages of λ2 and λ0 norms, enhancing sparse and smoothness, resulting in higher quality images with clearer details and preserved edges.
