Year-end Sale % OFF 
Abstract
Image dehazing on a hazy image aims to remove the haze and make the image scene clear, which attracts more and more research interests in recent years. Most existing image dehazing methods use a classic atmospheric scattering model and natural image priors to remove the image haze. In this paper, we propose an end-to-end image dehazing model termed as DRHNet (Deep Residual Haze Network), which restores the haze-free image by subtracting the learned negative residual map from the hazy image. Specifically, DRHNet proposes a context-aware feature extraction module to aggregate the contextual information effectively. Furthermore, it proposes a novel nonlinear activation function termed as RPReLU (Reverse Parametric Rectified Linear Unit) to improve its representation ability and to accelerate its convergence. Extensive experiments demonstrate that DRHNet outperforms state-of-the-art methods both quantitatively and qualitatively. In addition, experiments on image deraining task show that DRHNet can also serve for image deraining.
Highlights
The goal of the image dehazing algorithm is to restore a hazy image to a clear image, which has received significant research interest because various advanced image processing tasks require a clear scene (e.g., [1]–[6])
We apply the proposed Deep Residual Haze Network (DRHNet) for image deraining task, and the results show that DRHNet outperforms the other state-of-the-art image deraining methods, which demonstrates the generalizability of the proposed method
In this paper, we proposed a novel end-to-end deep residual haze network termed as DRHNet for single image dehazing and deraining
Summary
The goal of the image dehazing algorithm is to restore a hazy image to a clear image, which has received significant research interest because various advanced image processing tasks require a clear scene (e.g., [1]–[6]). Traditional image dehazing algorithms (e.g., [7], [8]) are dedicated to accurately estimate the transmission and the global atmospheric light in hazy images, and use the atmospheric scattering model to restore haze-free images. The associate editor coordinating the review of this manuscript and approving it for publication was Gang Li. where I (x) is the haze-degraded image, J (x) is the haze-free scene, α is the global atmospheric light, and t(x) is the scene transmission that describes the portion of the light that is not scattered and reaches the camera sensors. Most prior based image dehazing algorithms attempt to estimate t(x) and α and recover the haze-free scene using Eq (1)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
