Residual Spatial and Channel Attention Networks for Single Image Dehazing

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 treat spatial-wise and channel-wise features equally, but haze is practically unevenly distributed across an image, thus regions with different haze concentrations require different attentions. To solve these problems, we propose an end-to-end trainable densely connected residual spatial and channel attention network based on the conditional generative adversarial framework to directly restore a haze-free image from an input hazy image, without explicitly estimation of any atmospheric scattering parameters. Specifically, a novel residual attention module is proposed by combining spatial attention and channel attention mechanism, which could adaptively recalibrate spatial-wise and channel-wise feature weights by considering interdependencies among spatial and channel information. Such a mechanism allows the network to concentrate on more useful pixels and channels. Meanwhile, the dense network can maximize the information flow along features from different levels to encourage feature reuse and strengthen feature propagation. In addition, the network is trained with a multi-loss function, in which contrastive loss and registration loss are novel refined to restore sharper structures and ensure better visual quality. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.

Efficient Image Super-Resolution via Self-Calibrated Feature Fuse

“…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.…”

An Efficient Attentional Image Dehazing Deep Network Using Two Color Space (ADMC2-net)

“…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.…”

“…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.…”

Universal Image Restoration with Text Prompt Diffusion

“…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.…”