Abstract:Single image dehazing is a highly challenging ill-posed problem. Existing methods including both prior-based and learning-based heavily rely on the conceptual simplified atmospheric scattering model by estimating the so-called medium transmission map and atmospheric light. However, the formation of haze in the real world is much more complicated and inaccurate estimations further degrade the dehazing performance with color distortion, artifacts and insufficient haze removal. Moreover, most dehazing networks tr… Show more
“…The reconstruction part in SCFFN adopts NN, the SCA of our design and two convolutional layers. We conclude from previous work that attention mechanisms [ 30 , 31 ] can improve network performance, but there is little work on the impact of the reconstruction stage on network performance. Therefore, in this work, we employ an attention mechanism-based U-SCA block in the reconstruction phase to better reconstruct images.…”
Recently, many super-resolution reconstruction (SR) feedforward networks based on deep learning have been proposed. These networks enable the reconstructed images to achieve convincing results. However, due to a large amount of computation and parameters, SR technology is greatly limited in devices with limited computing power. To trade-off the network performance and network parameters. In this paper, we propose the efficient image super-resolution network via Self-Calibrated Feature Fuse, named SCFFN, by constructing the self-calibrated feature fuse block (SCFFB). Specifically, to recover the high-frequency detail information of the image as much as possible, we propose SCFFB by self-transformation and self-fusion of features. In addition, to accelerate the network training while reducing the computational complexity of the network, we employ an attention mechanism to elaborate the reconstruction part of the network, called U-SCA. Compared with the existing transposed convolution, it can greatly reduce the computation burden of the network without reducing the reconstruction effect. We have conducted full quantitative and qualitative experiments on public datasets, and the experimental results show that the network achieves comparable performance to other networks, while we only need fewer parameters and computational resources.
“…The reconstruction part in SCFFN adopts NN, the SCA of our design and two convolutional layers. We conclude from previous work that attention mechanisms [ 30 , 31 ] can improve network performance, but there is little work on the impact of the reconstruction stage on network performance. Therefore, in this work, we employ an attention mechanism-based U-SCA block in the reconstruction phase to better reconstruct images.…”
Recently, many super-resolution reconstruction (SR) feedforward networks based on deep learning have been proposed. These networks enable the reconstructed images to achieve convincing results. However, due to a large amount of computation and parameters, SR technology is greatly limited in devices with limited computing power. To trade-off the network performance and network parameters. In this paper, we propose the efficient image super-resolution network via Self-Calibrated Feature Fuse, named SCFFN, by constructing the self-calibrated feature fuse block (SCFFB). Specifically, to recover the high-frequency detail information of the image as much as possible, we propose SCFFB by self-transformation and self-fusion of features. In addition, to accelerate the network training while reducing the computational complexity of the network, we employ an attention mechanism to elaborate the reconstruction part of the network, called U-SCA. Compared with the existing transposed convolution, it can greatly reduce the computation burden of the network without reducing the reconstruction effect. We have conducted full quantitative and qualitative experiments on public datasets, and the experimental results show that the network achieves comparable performance to other networks, while we only need fewer parameters and computational resources.
“…Several studies [ 28 , 29 , 30 ] have employed this mechanism to enhance the effectiveness of DNN-based dehazing models by incorporating channel attention, pixel attention or both. However, these attempts failed to yield satisfactory results because of the difficulty of tackling intense haze in scenarios with dense haze, the complexity for integration to other existing DNN-based dehazing methods, and limited robustness due to sensitivity to some variations, such as scene complexity, lightning conditions, or weather.…”
“…CP-net [ 27 ] incorporates a double attention module (DA), and FFA-net [ 28 ] introduces a powerful feature attention module along a basic residual block. Furthermore, an effective network was introduced in [ 29 ] it comprises a residual spatial and channel attention module to adaptively adjust feature weights, considering haze distribution, enhancing feature representation and dehazing performance. Moreover, Sun et al [ 30 ] have proposed a fast and robust semi-supervised dehazing method (SADnet) that incorporates both channel and spatial attention mechanisms.…”
Section: Related Workmentioning
confidence: 99%
“…It is evident that the above-discussed attention-based models [ 26 , 27 , 28 , 29 , 30 ] can exhibit notable improvements in enhancing dehazing robustness. They outperform existing end-to-end models, showcasing their efficacy in addressing haze-related challenges.…”
Image dehazing has become a crucial prerequisite for most outdoor computer applications. The majority of existing dehazing models can achieve the haze removal problem. However, they fail to preserve colors and fine details. Addressing this problem, we introduce a novel high-performing attention-based dehazing model (ADMC2-net)that successfully incorporates both RGB and HSV color spaces to maintain color properties. This model consists of two parallel densely connected sub-models (RGB and HSV) followed by a new efficient attention module. This attention module comprises pixel-attention and channel-attention mechanisms to get more haze-relevant features. Experimental results analyses can validate that our proposed model (ADMC2-net) can achieve superior results on synthetic and real-world datasets and outperform most of state-of-the-art methods.
“…While single-task image restoration methods [ 1 , 2 , 3 , 4 , 5 , 32 , 33 , 34 , 35 ] have matured over time, universal image restoration methods are currently still in the early stages of development. Universal image restoration refers to the use of a single model to handle various types of degradation, also known as “all-in-one” image restoration.…”
Universal image restoration (UIR) aims to accurately restore images with a variety of unknown degradation types and levels. Existing methods, including both learning-based and prior-based approaches, heavily rely on low-quality image features. However, it is challenging to extract degradation information from diverse low-quality images, which limits model performance. Furthermore, UIR necessitates the recovery of images with diverse and complex types of degradation. Inaccurate estimations further decrease restoration performance, resulting in suboptimal recovery outcomes. To enhance UIR performance, a viable approach is to introduce additional priors. The current UIR methods have problems such as poor enhancement effect and low universality. To address this issue, we propose an effective framework based on a diffusion model (DM) for universal image restoration, dubbed ETDiffIR. Inspired by the remarkable performance of text prompts in the field of image generation, we employ text prompts to improve the restoration of degraded images. This framework utilizes a text prompt corresponding to the low-quality image to assist the diffusion model in restoring the image. Specifically, a novel text–image fusion block is proposed by combining the CLIP text encoder and the DA-CLIP image controller, which integrates text prompt encoding and degradation type encoding into time step encoding. Moreover, to reduce the computational cost of the denoising UNet in the diffusion model, we develop an efficient restoration U-shaped network (ERUNet) to achieve favorable noise prediction performance via depthwise convolution and pointwise convolution. We evaluate the proposed method on image dehazing, deraining, and denoising tasks. The experimental results indicate the superiority of our proposed algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.