Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most existing train a model on synthetic hazy images, which are less able to generalize well real images due domain shift. To address this issue, we propose adaptation paradigm, consists of an image translation module and two modules. Specifically, first apply bidirectional network bridge the gap between domains by translating from one another. And then, use before after proposed...

We present an effective semi-supervised learning algorithm for single image dehazing. The proposed applies a deep Convolutional Neural Network (CNN) containing supervised branch and unsupervised branch. In the branch, neural network is constrained by loss functions, which are mean squared, perceptual, adversarial losses. we exploit properties of clean images via sparsity dark channel gradient priors to constrain network. train on both synthetic data real-world in end-to-end manner. Our...

We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that good prior should favor clear images over blurred ones. In this work, we formulate as binary classifier which can be achieved deep convolutional neural network (CNN). The learned able to distinguish whether input or not. Embedded into maximum posterior (MAP) framework, it helps in various scenarios, including natural, face, text, and low-illumination...

Dynamic scene blur is usually caused by object motion, depth variation as well camera shake. Most existing methods solve this problem using image segmentation or fully end-to-end trainable deep convolutional neural networks considering different motions shakes. However, these algorithms are less effective when there exist variations. In work, we propose a network that exploits the map for dynamic deblurring. Given blurred image, first extract and adopt refinement to restore edges structure...

We propose a Generative Transfer Network (GTNet) for zero-shot object detection (ZSD). GTNet consists of an Object Detection Module and Knowledge Module. The can learn large-scale seen domain knowledge. leverages feature synthesizer to generate unseen class features, which are applied train new classification layer the In order synthesize features each with both intra-class variance IoU variance, we design IoU-Aware Adversarial (IoUGAN) as synthesizer, be easily integrated into GTNet....

We present an effective blind image deblurring method based on a data-driven discriminative prior.Our work is motivated by the fact that good prior should favor clear images over blurred images.In this work, we formulate as binary classifier which can be achieved deep convolutional neural network (CNN).The learned able to distinguish whether input or not.Embedded into maximum posterior (MAP) framework, it helps in various scenarios, including natural, face, text, and low-illumination...

In this paper, a multi-scale bias field estimation is proposed to carry out the aero-thermal radiation correction. The estimated at scales from coarse fine by an alternative minimization, after which, degraded image restored via subtraction. Tiknov regularization employed constrain smoothness of while Total Variation (TV) adopted preserve details and structures latent image. Besides, Split Bregman iteration introduced conquer difficulty in non-smooth problem when resolving minimization....

Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most existing train a model on synthetic hazy images, which are less able to generalize well real images due domain shift. To address this issue, we propose adaptation paradigm, consists of an image translation module and two modules. Specifically, first apply bidirectional network bridge the gap between domains by translating from one another. And then, use before after proposed...

We propose a Generative Transfer Network (GTNet) for zero shot object detection (ZSD). GTNet consists of an Object Detection Module and Knowledge Module. The can learn large-scale seen domain knowledge. leverages feature synthesizer to generate unseen class features, which are applied train new classification layer the In order synthesize features each with both intra-class variance IoU variance, we design IoU-Aware Adversarial (IoUGAN) as synthesizer, be easily integrated into GTNet....

In this paper, we propose a learning method for deblurring Gaussian blurred images blindly by exploiting edge cues via deep multi-scales generative adversarial network: DeepEdgeGAN. We proposed the edges of to be incorporated with image as input DeepEdgeGAN provide strong prior constraint restoration, which is beneficial solve problem that gradients restored GANs methods tend smooth and not clear enough. Further, introduce perceptual well scale losses train With trained end-to-end model,...

Image deblurring is to estimate the blur kernel and restore latent image. It usually divided into two stage, including estimation image restoration. In estimation, selecting a good region that contains structure information helpful accuracy of estimated kernel. Good deblur expert-chosen or in trial-anderror way. this paper, we apply metric named relative total variation (RTV) discriminate regions from smooth texture. Given blurry image, first calculate RTV each pixel determine whether it...