We propose a highly generative dehazing method based on pixel-wise Wasserstein autoencoders. In contrast to existing dehazing methods based on generative adversarial networks, our method can produce a variety of dehazed images with different styles. It significantly improves the dehazing accuracy via pixel-wise matching from hazy to dehazed images through 2-dimensional latent tensors of the Wasserstein autoencoder. In addition, we present an advanced feature fusion technique to deliver rich information to the latent space. For style transfer, we introduce a mapping function that transforms existing latent spaces to new ones. Thus, our method can produce highly generative haze-free images with various tones, illuminations, and moods, which induces several interesting applications, including low-light enhancement, daytime dehazing, nighttime dehazing, and underwater image enhancement. Experimental results demonstrate that our method quantitatively outperforms existing state-of-the-art methods for synthetic and real-world datasets, and simultaneously generates highly generative haze-free images, which are qualitatively diverse.

We present a novel dehazing framework for real-world images that contain both hazy and low-light areas. Dehazing and low-light enhancements are unified by using an illumination map that is estimated using a proposed convolutional neural network. The illumination map is then used as a component for three different tasks: atmospheric light estimation, transmission map estimation, and low-light enhancement, thereby enabling the solving of interrelated low-level vision problems simultaneously. To train the neural network to perform both dehazing and low-light enhancement, we synthesize hazy and low-light images from normal images. Experimental results demonstrate that the proposed method quantitatively and qualitatively outperforms state-of-the-art algorithms in real-world image dehazing.

In this paper, we propose a novel dehazing method based on self-distillation. In contrast to conventional knowledge distillation approaches that transfer large models (teacher networks) to small models (student networks), we introduce a single knowledge distillation network that transfers network parameters to itself for dehazing. In the early stages, the proposed network transfers scene content (identity) information to the next stage of itself using haze-free data. However, in the later stages, the network transfers haze information to itself using haze data, enabling the accurate dehazing of input images using scene information from the early stages. In a single network, parameters are seamlessly updated from extracting global scene features to dehazing the scene. During the training, forward propagation acts as a teacher network, whereas backward propagation acts as a student network. The experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art dehazing methods.

Image processing is a very fundamental technique in the field of low-level vision. However, with the development of deep learning over the past five years, most low-level vision methods tend to ignore this technique. Recent dehazing methods also refrain from using conventional image processing techniques, whereas only focusing on the development of new deep neural network (DNN) architectures. Unlike this recent trend, we show that image processing techniques are still competitive, if they are incorporated into DNNs. In this paper, we utilize conventional image processing techniques (i.e. curve adjustment, retinex decomposition, and multiple image fusion) for accurate dehazing. Moreover, we employ direct learning for stable dehazing performance. The proposed method can perform with low computational cost and easy to learn. The experimental results demonstrate that the proposed method produces accurate dehazing results compared to recent algorithms.

Accurate scale estimation and occlusion handling is a challenging problem in visual tracking. Recently, correlation filter-based trackers have shown impressive results in terms of accuracy, robustness, and speed. However, the model is not robust to scale variation and occlusion. In this paper, we address the problems associated with scale variation and occlusion by employing a scale space filter and multi-block scheme based on a kernelized correlation filter (KCF) tracker. Furthermore, we develop a more robust algorithm using an appearance update model that approximates the change of state of occlusion and deformation. In particular, an adaptive update scheme is presented to make each process robust. The experimental results demonstrate that the proposed method outperformed 29 state-of-the-art trackers on 100 challenging sequences. Specifically, the results obtained with the proposed scheme were improved by 8% and 18% compared to those of the KCF tracker for 49 occlusion and 64 scale variation sequences, respectively. Therefore, the proposed tracker can be a robust and useful tool for object tracking when occlusion and scale variation are involved.

In this paper, we propose a novel dual gradient-based desnowing algorithm that can accurately remove snow from a scene by characterizing snow particles. To localize snow in an image, we present a gradient-based snow activation map that can be estimated using snow classification. To recognize various patterns in the shapes and trajectories of snow particles, we introduce a gradient-based snow edge map. Using these two gradients, we estimate an accurate snow attention mask that is subsequently used for snow removal. In addition, we propose a translucency-aware context restoration network to handle various degrees of snow transparency and thus, prevent our method from losing the image context information during desnowing. Experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art desnowing algorithms quantitatively and qualitatively.